Vehicle avoidance method, apparatus, and device

Abstract

The application relates to the technical field of automatic driving, in particular to a vehicle avoiding method, device and equipment. The vehicle avoiding method comprises the following steps: when a vehicle is in an automatic driving state, determining whether a target vehicle exists in an adjacent lane, wherein the target vehicle comprises a large vehicle; when it is determined that the target vehicle exists in the adjacent lane, determining whether a current driving condition of the vehicle meets an avoiding condition; when it is determined that the current driving condition of the vehicle meets the avoiding condition, formulating an avoiding strategy according to the driving condition; and triggering lateral avoiding of the target vehicle in the lane according to the avoiding strategy. In the embodiment of the application, when the vehicle identifies that a target vehicle such as a large vehicle exists in the adjacent lane, lateral avoiding is triggered in the lane of the vehicle, the psychological burden of the driver is reduced, and the safety hidden danger caused by the collision between the vehicle and the target vehicle is reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of automatic driving, in particular to a vehicle avoiding method, device and equipment. BACKGROUND

[0002] With the continuous improvement of artificial intelligence, sensor technology and data processing capability in recent years, the automatic driving technology of vehicles is gradually moving towards commercialization and practical application. With the continuous strengthening of the hardware capability of vehicles, the automatic driving function needs to be more rich and humanized, and the current automatic driving application rate is higher in the scene of urban expressway, highway and the like. However, in this scene, large vehicles such as trucks, vans and dump trucks are often encountered. These large vehicles usually bring a sense of oppression to other vehicles in the adjacent lane, and if they normally drive in the center of the lane, it does not meet the driver's mental expectation, which brings a poor driving experience to the driver and other passengers in the vehicle, and there is also a certain safety risk. SUMMARY

[0003] The embodiments of the present application provide a vehicle avoiding method, device and equipment, to solve the problem that the driver is caused to have a sense of panic when driving alongside a large vehicle in the prior art.

[0004] In a first aspect, the embodiments of the present application provide a vehicle avoiding method, which comprises:

[0005] When the vehicle is in an automatic driving state, it is determined whether there is a target vehicle in the adjacent lane, and the target vehicle includes a large vehicle;

[0006] When it is determined that there is a target vehicle in the adjacent lane, it is determined whether the current driving condition of the vehicle meets an avoiding condition;

[0007] When it is determined that the current condition of the vehicle meets the avoiding condition, an avoiding strategy is formulated according to the driving condition;

[0008] According to the avoiding strategy, a lateral avoiding of the target vehicle in the lane is triggered.

[0009] Optionally, the current driving condition of the vehicle includes vehicle condition information, vehicle state information and target vehicle information;

[0010] The vehicle condition information includes lane width, lane radius, first longitudinal distance between the vehicle and the vehicle in the same direction on the avoiding side, and lane line confidence on the avoiding side;

[0011] The vehicle state information includes a first vehicle speed, a time length from the last time the avoiding is triggered, and whether there is another target vehicle on the avoiding side triggering the avoiding;

[0012] The target vehicle information includes a lateral distance between the target vehicle and the vehicle, and whether the target vehicle is an overtaking vehicle.

[0013] The avoidance side is a side opposite to a side of the vehicle identified to the target vehicle.

[0014] Optionally, the determining whether the current driving condition of the vehicle satisfies the avoidance condition comprises:

[0015] When the lane width is within a preset lane width range, the lane radius is greater than a preset lane radius threshold, a first longitudinal distance between the vehicle and a vehicle on the avoidance side is greater than a preset longitudinal distance threshold, and a lane line confidence on the avoidance side is higher than a preset confidence threshold, it is determined that the vehicle condition information satisfies the avoidance condition.

[0016] When the first vehicle speed is within a preset vehicle speed range, a time length from a last time when avoidance is triggered is greater than a preset first time threshold, and there is no other target vehicle on the avoidance side triggering avoidance, it is determined that the vehicle state information satisfies the avoidance condition.

[0017] When a lateral distance between the vehicle and the target vehicle is less than a preset lateral distance threshold, and the target vehicle is an overtaking vehicle, it is determined that the target vehicle information satisfies the avoidance condition.

[0018] When the vehicle condition information, the vehicle state information, and the target vehicle information simultaneously satisfy the avoidance condition, it is determined that the current driving condition of the vehicle satisfies the avoidance condition.

[0019] Optionally, the current driving condition of the vehicle further comprises a second longitudinal distance between the vehicle and the target vehicle, and a second vehicle speed of the target vehicle, and the formulating an avoidance strategy according to the driving condition comprises:

[0020] determining an avoidance distance when triggering execution of lateral avoidance according to the lane width;

[0021] determining a first time when a front of the vehicle and a rear of the target vehicle coincide in a horizontal position according to a speed difference between the first vehicle speed and the second vehicle speed and the second longitudinal distance;

[0022] determining a steering wheel rotation rate according to the avoidance distance and the first time, and determining a timing of starting to execute avoidance according to the first time and a preset second time threshold.

[0023] Optionally, the determining the avoidance distance when triggering execution of lateral avoidance according to the lane width comprises:

[0024] According to the lane width, a corresponding avoidance distance of the current lane width is determined from a preset corresponding relationship between lane widths and avoidance distances;

[0025] The corresponding relationship between the lane width and the avoidance distance is a corresponding relationship between a plurality of lane width ranges and a plurality of avoidance distances, and each lane width range corresponds to one avoidance distance.

[0026] Optionally, the determining whether the adjacent lane has the target vehicle comprises:

[0027] Collecting, by a vehicle-mounted sensor, to-be-recognized vehicle information of a vehicle in the adjacent lane;

[0028] Inputting the collected to-be-recognized vehicle information into a large vehicle recognition model that is pre-trained;

[0029] Determining, based on an output result of the large vehicle recognition model, whether the adjacent lane has the target vehicle.

[0030] Optionally, the method further comprises pre-training the large vehicle recognition model;

[0031] Collecting training information of each type of large vehicle;

[0032] Training the large vehicle recognition model by using the training information.

[0033] In a second aspect, an embodiment of the present application provides a vehicle avoidance device, and the device comprises:

[0034] A first determining module determines whether an adjacent lane has a target vehicle when a vehicle is in an automatic driving state, and the target vehicle comprises a large vehicle;

[0035] A second determining module determines whether a current driving condition of the vehicle meets an avoidance condition when it is determined that the adjacent lane has the target vehicle;

[0036] A formulating module formulates an avoidance strategy according to the driving condition when it is determined that the current condition of the vehicle meets the avoidance condition;

[0037] An avoidance module triggers a lateral avoidance of the target vehicle in the lane according to the avoidance strategy.

[0038] In a third aspect, an embodiment of the present application provides an electronic device, and the device comprises:

[0039] At least one processor; and

[0040] At least one memory in communication with the processor, wherein:

[0041] The memory stores program instructions executable by the processor, and the processor invoking the program instructions can execute the method of any one of the first aspect.

[0042] In a fourth aspect, an embodiment of the present application provides a storage medium, which comprises a stored program, wherein when the program runs, the device where the storage medium is located executes the method of any one of the first aspect.

[0043] In the embodiment of the present application, when the vehicle identifies that a target vehicle such as a large vehicle appears in the adjacent lane, the vehicle triggers to perform lateral avoidance in the lane of the vehicle, which reduces the psychological burden of the driver and reduces the safety hazards caused by the collision between the vehicle and the target vehicle. Meanwhile, before triggering to perform avoidance, the current driving condition of the vehicle is arbitrated based on the preset avoidance condition, and some redundant conditions are excluded, so as to avoid the vehicle from blindly performing avoidance in all condition scenes, so as to further reduce the driving experience of the driver. When performing avoidance, the avoidance strategy is formulated in combination with the current condition, so that the avoidance process is more in line with normal driving habits, and the whole process is more comfortable and humanized. BRIEF DESCRIPTION OF DRAWINGS

[0044] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments. Obviously, the drawings described in the following are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor.

[0045] Figure 1 Fig. 1 shows a flowchart of a vehicle avoidance method provided by an embodiment of the present application;

[0046] Figure 2 Fig. 2 shows a structural schematic diagram of a vehicle avoidance device provided by an embodiment of the present application;

[0047] Figure 3 Fig. 3 shows a structural schematic diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0048] In order to better understand the technical solutions of the present application, the embodiments of the present application will be described in detail below with reference to the drawings.

[0049] It should be clear that the described embodiments are only some embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0050] In order to avoid the panic feeling of the driver caused by large vehicles such as trucks on the expressway or highway and some unknown safety risks, the embodiment of the present application formulates an avoidance method for large vehicles such as trucks based on the current driving assistance system, when the host vehicle overtakes the target vehicle from the rear of the adjacent lane, a certain degree of lateral avoidance is performed within the lane line of the lane of the host vehicle, so as to reduce the panic feeling of the driver and reduce certain safety risks.

[0051] As shown in Figure 1 , a vehicle avoidance method provided by the embodiment of the present application. The method is applied to the driving assistance system in the vehicle, as shown in Figure 1 , the specific steps of the method include:

[0052] S101, when the vehicle is in an automatic driving state, determine whether there is a target vehicle in the adjacent lane, the target vehicle includes a large vehicle.

[0053] Specifically, when the vehicle is in an automatic driving state, the vehicle-mounted sensors carried by the vehicle, such as cameras, millimeter wave radars, laser radars and ultrasonic radars, collect the to-be-identified vehicle information of the vehicle in the adjacent lane. The collected to-be-identified vehicle information is input into a large vehicle identification model which is pre-trained, and the large vehicle identification model is used to identify the collected to-be-identified vehicle information, so as to determine whether there is a target vehicle, i.e. a large vehicle, in the adjacent lane.

[0054] Based on the output result of the large vehicle identification model, it is determined whether there is a target vehicle in the adjacent lane. When it is determined that there is a target vehicle in the adjacent lane, the corresponding prompt light on the instrument panel is lit, or the corresponding prompt information is displayed, so as to prompt the driver that there is a large vehicle in the adjacent lane.

[0055] Among them, the training of the large vehicle identification model needs to be completed in the auxiliary driving system in advance. When training the large vehicle identification model, vehicles that need to be avoided, such as trucks, dump trucks, large trucks, buses, etc. are classified as large vehicles, and training information of various types of large vehicles is collected. The large vehicle identification model is trained through the collected training information.

[0056] S102, when it is determined that there is a target vehicle in the adjacent lane, determine whether the current driving condition of the vehicle meets the avoidance condition.

[0057] Specifically, the current driving condition of the vehicle is obtained through the vehicle-mounted sensors carried by the vehicle. The driving condition includes vehicle condition information, vehicle state information and target vehicle information.

[0058] The vehicle information specifically includes lane width, lane radius, first longitudinal distance between the vehicle and the same-direction vehicle on the avoidance side, and lane line confidence on the avoidance side. The vehicle state information specifically includes first vehicle speed, time length since the last time the avoidance is triggered, and whether there is another target vehicle on the avoidance side triggering the avoidance. The target vehicle information specifically includes lateral distance between the target vehicle and the vehicle, and whether the target vehicle is a passable vehicle.

[0059] The collected driving conditions are arbitrated one by one. Only when the vehicle condition information, the vehicle state information, and the target vehicle information all meet the avoidance condition at the same time, it is determined that the current driving condition of the vehicle meets the avoidance condition, triggering the execution of the avoidance of the target vehicle.

[0060] Optionally, when any of the current driving conditions of the vehicle does not meet the avoidance condition, the avoidance is not triggered, and the vehicle is controlled to drive in the center of the lane line.

[0061] Specifically, when arbitrating the vehicle condition information, it is necessary to determine that the lane width is within a preset lane width range, the lane radius is greater than a preset lane radius threshold, the first longitudinal distance between the vehicle and the same-direction vehicle on the avoidance side is greater than a preset longitudinal distance threshold, and the lane line confidence on the avoidance side is higher than a preset confidence threshold, so as to determine that the vehicle condition information meets the avoidance condition.

[0062] Since there is no need to avoid in the case of a wide lane width, and in order to avoid the distance between the vehicle and the lane line on the avoidance side being too close after the avoidance is executed in the case of a narrow lane width, it is necessary to preset the upper limit and the lower limit of the lane line, that is, to preset the lane width range, and when the current lane width is within the preset lane width range, it is determined that the lane width meets the avoidance condition. Generally, the lane width range can be set to 3.4-5.5 meters.

[0063] Since in the case of a small curve radius, the vehicle may cut in or cut out when passing the curve through the automatic driving function, resulting in a poor driving experience of the driver, it is necessary to preset the lane radius threshold, and when the current lane radius is greater than the preset lane radius threshold, it is determined that the lane radius meets the avoidance condition. Generally, the lane radius threshold can be set to 1000 meters.

[0064] In order to avoid the distance between the vehicle and the same-direction vehicle on the avoidance side being too close after the avoidance is executed, or to avoid the avoidance triggered by the same-direction vehicle on the avoidance side, and thus causing the two sides to alternate avoidance, resulting in a poor driving experience of the driver, it is necessary to preset the longitudinal distance threshold, and when the first longitudinal distance between the vehicle and the same-direction vehicle on the avoidance side is greater than the preset longitudinal distance threshold, it is determined that the first longitudinal distance meets the avoidance condition. Generally, the longitudinal distance threshold is set to 10 meters.

[0065] In order to ensure stable control of the vehicle on the avoidance side, a preset lane line confidence threshold is required, and when it is determined that the lane line confidence of the avoidance side is higher than the preset confidence threshold, it is determined that the lane line confidence meets the avoidance condition.

[0066] When arbitrating the vehicle state information, when the first vehicle speed of the vehicle is within a preset vehicle speed range, and the time interval from the last time the avoidance is triggered is greater than a preset first time threshold, and there is no other target vehicle on the avoidance side triggering avoidance, it is determined that the vehicle state information meets the avoidance condition.

[0067] Since a slow vehicle speed will not cause stress to the driver, and a fast vehicle speed will directly affect the safety of autonomous driving, a vehicle speed upper limit and a lower limit need to be preset, i.e., a vehicle speed range needs to be preset. When it is determined that the first vehicle speed is within the preset vehicle speed range, it is determined that the first vehicle speed meets the avoidance condition. Generally, the vehicle speed range is set to 65kph-130kph.

[0068] In order to ensure that the distance from the front vehicle is always greater than 50 meters, a safety distance, at the vehicle speed requirement (≥65kph) for triggering the execution of avoidance, a first time threshold needs to be preset, and after completing an avoidance, the distance between the vehicle and the front vehicle is lengthened through this time. Therefore, when the vehicle is greater than the preset first time threshold from the last time the avoidance is triggered, it is determined that the time interval from the last time the avoidance is triggered meets the avoidance condition. Generally, the first time threshold is set to 3 seconds.

[0069] In order to avoid alternating avoidance on both sides of the lane, it is necessary to determine that there is no other target vehicle on the avoidance side triggering avoidance, and to determine that the avoidance condition is met.

[0070] When arbitrating the target vehicle information, when the lateral distance between the vehicle and the target vehicle is less than a preset lateral distance threshold, and the target vehicle is an overtaking vehicle, it is determined that the target vehicle information meets the avoidance condition.

[0071] Since a large lateral distance between the vehicle and the target vehicle will not cause stress to the driver, and blind avoidance will otherwise cause safety problems in autonomous driving, a lateral distance threshold is preset, and when the lateral distance between the vehicle and the target vehicle is less than the preset lateral distance threshold, it is determined that the lateral distance meets the avoidance condition. Generally, the lateral distance threshold is set to 4 meters.

[0072] In order to avoid safety problems when overtaking the target vehicle, and not to violate traffic laws, the vehicle type of the target vehicle needs to be determined. When it is determined that the target vehicle is an overtaking vehicle, it is determined that the avoidance condition is met.

[0073] In the above embodiments, the avoidance side is the side opposite to the side where the vehicle identifies the target vehicle. For example, when the vehicle identifies the target vehicle in the right lane, the avoidance side is the left side of the vehicle.

[0074] S103, when it is determined that the current working condition of the vehicle meets the avoidance condition, an avoidance strategy is formulated according to the driving working condition.

[0075] Specifically, the avoidance strategy specifically includes the avoidance time, the avoidance distance, and the steering wheel rotation rate.

[0076] According to the lane width of the current lane, the avoidance distance when triggering the execution of the lateral avoidance is determined from the preset corresponding relationship between the lane width and the avoidance distance.

[0077] According to the speed difference between the first vehicle speed and the second vehicle speed of the target vehicle, and the second longitudinal distance between the vehicle and the target vehicle, the first time when the vehicle head of the vehicle and the vehicle tail of the target vehicle coincide in horizontal position is determined. When it is determined that the first time is less than the preset second time threshold, it is determined that the time is the time to start the avoidance.

[0078] Further, the steering wheel rotation rate is determined according to the determined avoidance distance and the determined first time. That is, the steering wheel rotation rate is determined by dividing the avoidance distance by the first time and converting.

[0079] In order to avoid the problem of poor driving experience caused by the avoidance distance constantly jumping due to the change of the lane width, the preset corresponding relationship between the lane width and the avoidance distance is a corresponding relationship between a plurality of lane ranges and a plurality of avoidance distances, each lane range corresponds to one avoidance distance. That is, the specific lane width and the avoidance distance are in a discrete corresponding relationship, and a plurality of lane widths in the same range correspond to the same avoidance distance.

[0080] In one specific embodiment, when the vehicle is centered in the lane of 3.4-4.2 meters, when the lane width is 3.4-3.8 meters, the avoidance distance is 0.1 meters; when the lane width is 3.8-4.2 meters, the avoidance distance is 0.2 meters.

[0081] S104, triggering the lateral avoidance of the target vehicle in the lane according to the avoidance strategy.

[0082] Specifically, according to the avoidance strategy determined, that is, the avoidance time, the avoidance distance, and the steering wheel rotation rate, the lateral avoidance of the target vehicle is triggered in the lane line of the ego vehicle to the avoidance side, so that the vehicle head of the vehicle and the vehicle tail of the target vehicle coincide in horizontal position when the avoidance is completed. This can reduce the panic of the driver and avoid dangerous situations.

[0083] In the embodiments of the present application, when the vehicle identifies that a target vehicle such as a large vehicle appears in the adjacent lane, the vehicle triggers to perform lateral avoidance in the lane of the vehicle, which reduces the psychological burden of the driver and reduces the safety hazards caused by the collision between the vehicle and the target vehicle. Meanwhile, before triggering to perform avoidance, the current driving condition of the vehicle is arbitrated based on the preset avoidance condition, and some redundant conditions are excluded, so as to avoid the vehicle from blindly performing avoidance in all condition scenes, so as to further reduce the driving experience of the driver. When performing avoidance, the avoidance strategy is formulated in combination with the current condition, so that the avoidance process is more in line with normal driving habits, and the whole process is more comfortable and humanized.

[0084] Corresponding to the above vehicle avoidance method, the embodiments of the present application also provide a vehicle avoidance device. Referring to Figure 2 A structural schematic diagram of a vehicle avoidance device provided by the embodiments of the present application, the vehicle avoidance device can include a first determination module 201, a second determination module 202, a formulation module 203 and an avoidance module 204.

[0085] The first determination module 201 determines whether there is a target vehicle in the adjacent lane when the vehicle is in an automatic driving state, and the target vehicle includes a large vehicle.

[0086] The second determination module 202 determines whether the current driving condition of the vehicle meets the avoidance condition when it is determined that there is a target vehicle in the adjacent lane.

[0087] The formulation module 203 formulates an avoidance strategy according to the driving condition when it is determined that the current condition of the vehicle meets the avoidance condition.

[0088] The avoidance module 204 triggers lateral avoidance of the target vehicle in the lane according to the avoidance strategy.

[0089] Figure 3 A structural schematic diagram of an electronic device for an embodiment of the present specification. As Figure 3 shown, the above electronic device can include at least one processor; and at least one memory in communication connection with the above processing unit, wherein: the memory stores program instructions that can be executed by the processing unit, and the above processor calling the above program instructions can execute the vehicle avoidance method provided by the embodiments.

[0090] Among them, the above electronic device can be a device capable of intelligent conversation with the user, for example: a cloud server, and the embodiments of the present specification do not limit the specific form of the above electronic device. It can be understood that the electronic device here is the machine mentioned in the method embodiments.

[0091] Figure 3A block diagram of an exemplary electronic device suitable for use in implementing the embodiments of the present specification is shown. Figure 3 The electronic device shown is merely one example. It should be understood, however, that the functions and uses of the embodiments of the present specification are not limited to this example.

[0092] As Figure 3 The electronic device is shown in the form of a general purpose computing device. The components of the electronic device can include, but are not limited to, one or more processors 310, a communication interface 320, a memory 330, a communication bus 340 that connects different system components including the memory 330, the communication interface 320, and the processor 310.

[0093] The communication bus 340 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration bus, a processor or local bus using any of a variety of bus architectures. By way of example, these architectures include 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.

[0094] The electronic device typically includes a variety of computer system readable media. Such media can be any available media that is accessible by the electronic device and includes both volatile and non-volatile media, removable and non-removable media.

[0095] The memory 330 can include computer system readable media in the form of volatile memory, such as random access memory (RAM) and / or cache memory. The electronic device can further include other removable / non-removable, volatile / non-volatile computer system storage media. The memory 330 can include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the present specification.

[0096] The program / utility, having a set of program modules, can be stored in memory 330, for execution by the processing unit 310, as well as an operating system, one or more application programs, other program modules, and program data, each or some combination thereof, can include implementation of the network environment. Generally, program modules are executed by the processing unit 310 in the memory 330, as described above. Programs (also known as applications) stored on the computer-readable medium 320 can include programs implementing embodiments of the present description.

[0097] The processor 310 performs various function applications and data processing by running programs stored in the memory 330, such as implementing the vehicle avoidance method provided by the embodiments of the present description.

[0098] The embodiments of the present description provide a non-transitory computer-readable storage medium storing computer instructions, which cause the computer to perform the vehicle avoidance method provided by the embodiments of the present description.

[0099] The non-transitory computer-readable storage medium described above can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or apparatus, or any combination thereof. More specific examples (non-exhaustive list) of the computer-readable storage medium include an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), or a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this document, the computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus, or device.

[0100] The computer-readable signal medium can include a data signal carried in a baseband or as part of a carrier wave, in which the computer-readable program code is carried. Such a propagated data signal can take a variety of forms, including, but not limited to, an electromagnetic signal, an optical signal, or any suitable combination thereof. The computer-readable signal medium can also be any computer-readable medium that is not a storage medium and that can be used to carry or store computer-readable program code, which can be used by or in connection with an instruction execution system, apparatus, or device.

[0101] The program code embodied on the computer readable media can be transmitted using any appropriate medium, including but not limited to wireless, wire line, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0102] Computer program code for carrying out operations of the present specification can be written in any suitable programming language including object oriented programming languages, such as Java, Smalltalk, C++, as well as conventional procedural programming languages, such as the "C" programming language, or the like. The program code can 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 the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0103] The specific embodiments of the present specification have been described. Other embodiments are within the scope of the following claims. In some cases, the actions recited in the claims can be performed in a different order and still achieve desirable results. Additionally, the process depicted in the figures does not necessarily require the particular order shown, or sequential order to achieve the desired results. In certain implementations, multitasking and parallel processing can be advantageous.

[0104] In addition, the terms "first", "second", etc., are used herein only to describe different instances, and do not imply or suggest relative importance or a number of indicated technical features. Thus, the features defined with "first", "second" can explicitly or implicitly include at least one of the features. In the description of the specification, the meaning of "a plurality of" is at least two, for example, two, three, etc., unless otherwise explicitly specified.

[0105] Any process or method descriptions or descriptions of processes or methods contained herein can be understood as representing any manner of executing steps of the process or method, and any suitable sequence of steps can be employed, including substantially simultaneous execution of the steps of the process or method, or in reverse order of the steps for described processes or methods. The scope of preferred embodiments of the present specification includes any suitable process or method that implements or utilizes the described features any number of ways.

[0106] Depending on the context, the word "if" as used herein can be interpreted to mean "when" or "while" or "in response to determining" or "in response to detecting." Similarly, the phrase "if it is determined" or "if [a stated condition or event] is detected" can be interpreted to mean "when it is determined" or "in response to determining" or "when [the stated condition or event] is detected" or "in response to detecting [the stated condition or event]."

[0107] It should be noted that the terminal involved in the embodiments of the present specification can include, but is not limited to, a personal computer (PC), a personal digital assistant (PDA), a wireless handheld device, a tablet computer, a mobile phone, an MP3 player, an MP4 player, and the like.

[0108] In the embodiments provided by the present specification, it should be understood that the disclosed system, device and method can be implemented in other ways. For example, the device embodiments described above are only schematic. The division of the units is only a logical function division. There can be another division manner in actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or in other forms.

[0109] In addition, each functional unit in each embodiment of the present specification can be integrated into one processing unit, or each unit can exist physically independently, or two or more units can be integrated into one unit. The above integrated unit can be realized in the form of hardware, or in the form of hardware plus software function unit.

[0110] The integrated unit realized in the form of software function unit can be stored in a computer readable storage medium. The software function unit stored in the storage medium includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute part of the steps of the method described in each embodiment of the present specification.

[0111] The above only describes the preferred embodiments of the present specification and is not intended to limit the present specification. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present specification shall be included in the scope of protection of the present specification.

Claims

1. A vehicle evasion method characterized by, The method comprises: determining whether there is a target vehicle in the adjacent lane when the vehicle is in an automatic driving state, the target vehicle including a large vehicle; determining whether the current driving condition of the vehicle meets an avoidance condition when it is determined that there is a target vehicle in the adjacent lane; formulating an avoidance strategy according to the driving condition when it is determined that the current condition of the vehicle meets the avoidance condition; triggering lateral avoidance of the target vehicle in the lane according to the avoidance strategy; the current driving condition of the vehicle includes vehicle condition information, vehicle state information and target vehicle information; the vehicle condition information includes lane width, lane radius, first longitudinal distance between the vehicle and a vehicle in the same direction on the avoidance side, lane line confidence on the avoidance side; the vehicle state information includes first vehicle speed, time length since the last time avoidance was triggered, and whether there is another target vehicle on the avoidance side triggering avoidance; the target vehicle information includes lateral distance between the vehicle and the target vehicle, and whether the target vehicle is a passable vehicle; wherein the avoidance side is the opposite side of the side of the vehicle on which the target vehicle is recognized; the determination of whether the current driving condition of the vehicle meets the avoidance condition comprises: when the lane width is within a preset lane width range, the lane radius is greater than a preset lane radius threshold, the first longitudinal distance between the vehicle and the vehicle in the same direction on the avoidance side is greater than a preset longitudinal distance threshold, and the lane line confidence on the avoidance side is higher than a preset confidence threshold, it is determined that the vehicle condition information meets the avoidance condition; when the first vehicle speed is within a preset vehicle speed range, the time length since the last time avoidance was triggered is greater than a preset first time threshold, and there is no other target vehicle on the avoidance side triggering avoidance, it is determined that the vehicle state information meets the avoidance condition; when the lateral distance between the vehicle and the target vehicle is less than a preset lateral distance threshold, and the target vehicle is a passable vehicle, it is determined that the target vehicle information meets the avoidance condition; when the vehicle condition information, the vehicle state information and the target vehicle information all meet the avoidance condition, it is determined that the current driving condition of the vehicle meets the avoidance condition.

2. The method of claim 1, wherein, The current driving condition of the vehicle further includes a second longitudinal distance between the vehicle and the target vehicle, and a second vehicle speed of the target vehicle, and the formulation of the avoidance strategy according to the driving condition comprises: determining an avoidance distance when triggering lateral avoidance according to the lane width; determining a first time when the front of the vehicle and the rear of the target vehicle coincide in horizontal position according to the speed difference between the first vehicle speed and the second vehicle speed, and the second longitudinal distance; determining the steering wheel rotation rate according to the avoidance distance and the first time, and determining the timing of starting to perform avoidance according to the first time and a preset second time threshold.

3. The method of claim 2, wherein, The determination of the avoidance distance when triggering lateral avoidance according to the lane width comprises: determining the avoidance distance corresponding to the current lane width from the preset lane width and avoidance distance correspondence. The corresponding relationship between the lane width and the avoidance distance is a corresponding relationship between a plurality of lane width ranges and a plurality of avoidance distances, and each lane width range corresponds to one avoidance distance.

4. The method of claim 1, wherein, The determining whether the adjacent lane has the target vehicle comprises: Collecting, by a vehicle-mounted sensor, to-be-identified vehicle information of a vehicle in the adjacent lane; Inputting the collected to-be-identified vehicle information into a pre-trained large vehicle identification model; Determining, based on an output result of the large vehicle identification model, whether the adjacent lane has the target vehicle.

5. The method of claim 4, wherein, The method further comprises: Collecting training information of each type of large vehicle; Training the large vehicle identification model based on the training information.

6. A vehicle avoidance apparatus characterized by, The device comprises: A first determining module configured to determine whether an adjacent lane has a target vehicle when a vehicle is in an automatic driving state, wherein the target vehicle comprises a large vehicle; A second determining module configured to determine whether a current driving condition of the vehicle meets an avoidance condition when it is determined that the adjacent lane has the target vehicle; A formulating module configured to formulate an avoidance strategy according to the driving condition when it is determined that the current driving condition of the vehicle meets the avoidance condition; An avoidance module configured to trigger lateral avoidance of the target vehicle in the lane according to the avoidance strategy; The current driving condition of the vehicle comprises vehicle condition information, vehicle state information and target vehicle information; The vehicle condition information comprises a lane width, a lane radius, a first longitudinal distance between the vehicle and a same-direction vehicle on an avoidance side, and lane line confidence on the avoidance side; The vehicle state information comprises a first vehicle speed, a time length from a last time when avoidance is triggered, and whether there is another target vehicle on the avoidance side triggering avoidance; The target vehicle information comprises a lateral distance between the vehicle and the target vehicle, and whether the target vehicle is a passable vehicle; The avoidance side is a side opposite to a side on which the vehicle recognizes the target vehicle; The determining whether the current driving condition of the vehicle meets the avoidance condition comprises: When the lane width is within a preset lane width range, the lane radius is greater than a preset lane radius threshold, the first longitudinal distance between the vehicle and the same-direction vehicle on the avoidance side is greater than a preset longitudinal distance threshold, and the lane line confidence on the avoidance side is higher than a preset confidence threshold, it is determined that the vehicle condition information meets the avoidance condition; When the first vehicle speed is within a preset vehicle speed range, the time length from the last time when avoidance is triggered is greater than a preset first time threshold, and there is no other target vehicle on the avoidance side triggering avoidance, it is determined that the vehicle state information meets the avoidance condition; When the lateral distance between the vehicle and the target vehicle is less than a preset lateral distance threshold, and the target vehicle is a passable vehicle, it is determined that the target vehicle information meets the avoidance condition; When the vehicle condition information, the vehicle state information and the target vehicle information all meet the avoidance condition, it is determined that the current driving condition of the vehicle meets the avoidance condition.

7. An electronic device, comprising: The device comprises: At least one processor; and At least one memory connected with the processor, wherein: The memory stores program instructions executable by the processor, and the processor invoking the program instructions is capable of executing the method according to any one of claims 1 to 5.

8. A storage medium, characterized by The storage medium comprises a stored program, wherein the program, when executed, controls a device in which the storage medium is located to execute the method according to any one of claims 1 to 5.

Images