Method and device for planning vehicle driving path, storage medium and electronic equipment

Abstract

The embodiment of the invention relates to the technical field of intelligent driving, and provides a method and device for planning a vehicle driving path, a storage medium and electronic equipment. The method comprises the following steps: determining at least one second vehicle within a preset range from a first vehicle; determining a vehicle type of the at least one second vehicle; determining a first duration when the at least one second vehicle appears in a preset range; generating an avoidance instruction based on the vehicle type and the first duration; and planning a driving path of the first vehicle based on the avoidance instruction. Therefore, according to the technical scheme provided by the embodiment of the invention, the second vehicles which are of the preset type and continuously appear in the preset range and are greater than or equal to the preset time threshold value can be accurately screened out from the second vehicles appearing in the preset range around the first vehicle, and the driving path is re-planned based on the second vehicles; therefore, not only can the second vehicle of the preset type be avoided in a targeted manner, but also frequent avoidance can be avoided.

Description

Technical Field

[0001] The present disclosure relates to the field of intelligent driving technology, and particularly to a method, device, storage medium and electronic device for planning a driving path of a vehicle. Background Art

[0002] An intelligent driving system is a system for realizing automatic driving of a vehicle, aiming to improve driving safety and comfort.

[0003] During the process of controlling a vehicle to drive based on an intelligent driving system, vehicles driving around the present vehicle are one of the important factors threatening driving safety. Therefore, the driving path of the present vehicle can be re-planned based on the surrounding vehicles to automatically avoid the surrounding vehicles, thereby improving driving safety. Summary of the Invention

[0004] In order to improve the driving safety of the present vehicle, it will automatically avoid other vehicles driving around it. If the present vehicle avoids other vehicles driving around it without discrimination, it may lead to the problem of not being able to accurately avoid vehicles of a preset type, or it may lead to frequently avoiding vehicles passing by around, thereby threatening the safety of the present vehicle.

[0005] To solve the above technical problems, the present disclosure provides a method, device, storage medium and electronic device for planning a driving path of a vehicle, which can effectively solve the problems of not being able to accurately avoid vehicles of a preset type and frequently avoiding vehicles passing by around.

[0006] In the first aspect of the present disclosure, a method for planning a driving path of a vehicle is provided. The method includes: determining at least one second vehicle within a preset range from a first vehicle; determining the vehicle type of the at least one second vehicle; determining a first duration for which the at least one second vehicle appears within the preset range; generating an avoidance instruction based on the vehicle type and the first duration; and planning the driving path of the first vehicle based on the avoidance instruction.

[0007] In the second aspect of the present disclosure, a device for planning a driving path of a vehicle is provided. The device includes: a sensing module for determining at least one second vehicle within a preset range from a first vehicle; an identification module for determining the vehicle type of the at least one second vehicle; the identification module is further used for determining a first duration for which the at least one second vehicle appears within the preset range; a decision module for generating an avoidance instruction based on the vehicle type and the first duration; and a planning module for planning the driving path of the first vehicle based on the avoidance instruction.

[0008] In a third aspect of the present disclosure, embodiments of the present disclosure provide a computer-readable storage medium storing a computer program for executing the method for planning a vehicle driving route provided in the first aspect.

[0009] In a fourth aspect of the present disclosure, embodiments of the present disclosure provide an electronic device including: a processor; and a memory for storing executable instructions executable by the processor, wherein the processor is configured to read the executable instructions from the memory and execute the executable instructions to implement the method for planning a vehicle driving route provided in the first aspect.

[0010] Based on the method for planning a vehicle driving route provided by the present disclosure, at least one second vehicle within a preset range from a first vehicle is determined, the vehicle type of the at least one second vehicle is determined, and a first duration for which the at least one second vehicle appears within the preset range is determined. Based on the vehicle type and the first duration, an avoidance instruction is generated, and based on the avoidance instruction, a driving route of the first vehicle is planned. Thus, it is possible to accurately screen out second vehicles of a preset type that continuously appear within the preset range for greater than or equal to a preset time threshold from the second vehicles appearing within the preset range around the first vehicle, and re-plan the driving route based on the second vehicle, so that not only can the second vehicles of the preset type be avoided in a targeted manner, but also frequent avoidance can be avoided. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 is a structural block diagram of a vehicle avoidance system provided by an exemplary embodiment of the present disclosure;

[0012] Figure 2A is a schematic diagram of the total sensing area of a sensing system provided by an exemplary embodiment of the present disclosure;

[0013] Figure 2B is a schematic diagram of a preset range provided by an exemplary embodiment of the present disclosure;

[0014] Figure 3 is a schematic flowchart of a method for planning a vehicle driving route provided by an exemplary embodiment of the present disclosure;

[0015] Figure 4 is a flowchart of a method for planning a vehicle driving route provided by another exemplary embodiment of the present disclosure;

[0016] Figure 5 is a flowchart of a method for planning a vehicle driving route provided by another exemplary embodiment of the present disclosure;

[0017] Figure 6 is a flowchart of a method for planning a vehicle driving route provided by another exemplary embodiment of the present disclosure;

[0018] Figure 7 It is a flowchart of a method for planning a vehicle driving path provided by another exemplary embodiment of the present disclosure;

[0019] Figure 8 It is a flowchart of a method for setting a preset type provided by an exemplary embodiment of the present disclosure;

[0020] Figure 9 It is a flowchart of a method for real-time setting of a preset type provided by an exemplary embodiment of the present disclosure;

[0021] Figure 10 It is a flowchart of a method for determining the matching relationship between a vehicle type and a preset type provided by an exemplary embodiment of the present disclosure;

[0022] Figure 11 It is a flowchart of a method for planning a vehicle driving path provided by an exemplary embodiment of the present disclosure;

[0023] Figure 12 It is a schematic structural diagram of a vehicle avoidance device provided by an exemplary embodiment of the disclosure;

[0024] Figure 13 It is a structural diagram of an electronic device provided by the present disclosure. Detailed implementation manners

[0025] To explain the present disclosure, exemplary embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all the embodiments. It should be understood that the present disclosure is not limited by the exemplary embodiments.

[0026] It should be noted that: unless otherwise specifically stated, the relative arrangements of components and steps, numerical expressions, and numerical values set forth in these embodiments do not limit the scope of the present disclosure.

[0027] Overview of the Application

[0028] During the driving process of the present vehicle, the vehicles driving around are one of the important factors threatening the driving safety of the present vehicle. For example, the vehicles driving around the present vehicle may cause psychological pressure on the driver, and once a collision occurs, it will cause damage to property and personal safety. Therefore, the function of avoiding the surrounding vehicles is an important function for improving the driving safety of the present vehicle.

[0029] To improve the driving safety of the present vehicle, it will automatically avoid other vehicles driving around it. If the present vehicle avoids other vehicles driving around it without discrimination, it may lead to the problem of being unable to accurately avoid preset type vehicles, or it may lead to frequently avoiding the surrounding passing vehicles, thereby threatening the safety of the present vehicle.

[0030] Embodiments of the present disclosure provide a method, an apparatus, a storage medium, and an electronic device for planning a vehicle driving route, which can optimize the vehicle avoidance function so that the vehicle can accurately avoid vehicles of a preset type during driving and can avoid frequently avoiding surrounding passing vehicles.

[0031] Exemplary System

[0032] Figure 1 It is a structural block diagram of a vehicle avoidance system provided by an exemplary embodiment of the present disclosure.

[0033] Among them, the vehicle avoidance system can be applied to autonomous vehicles. The vehicle to which the vehicle avoidance system is applied (the first vehicle) is referred to as the first vehicle, and the vehicles around the first vehicle are referred to as the second vehicles.

[0034] As Figure 1 shown, in one embodiment, the vehicle avoidance system may include a perception system 10, a decision-making system 20, and a driving control system 30. The decision-making system 20 is communicatively connected to the perception system 10 and the driving control system 30 respectively. In this way, the decision-making system 20 can perform information interaction with the perception system 10 and the driving control system 30 respectively.

[0035] In one implementation, the perception system 10 is used to collect environmental data around the first vehicle. The perception system 10 may include at least one sensor, such as an image sensor. Among them, the image sensor may include at least one of a monocular camera, a binocular camera, a trinocular camera, a wide-angle camera, and a fish-eye camera. Embodiments of the present disclosure do not limit the type of the image sensor. In this way, the perception system 10 can collect videos or pictures around the first vehicle.

[0036] In one example, the video collected by the perception system 10 may include images of objects (such as the second vehicle), lane lines, traffic signs, etc. around the first vehicle.

[0037] The perception system 10 may include at least one image sensor, and the at least one image sensor may be installed at different positions of the first vehicle to collect environmental data in different directions. For example, the image sensor may be installed at the head of the first vehicle to collect environmental data in front of the first vehicle. The image sensor may be installed at the tail of the first vehicle to collect environmental data behind the first vehicle. The image sensor may be installed at the side of the first vehicle to collect environmental data on the side of the first vehicle.

[0038] The perception area of the image sensor refers to the maximum shooting range of the image sensor, and the perception area of the image sensor is determined by the shooting parameters of the image sensor, such as the field of view (FOV), shooting distance, etc.

[0039] In one example, if the field of view angle and the shooting distance of the image sensor are small, the sensing area of the image sensor is small. If the field of view angle and the shooting distance of the image sensor are large, the sensing area of the image sensor is large.

[0040] Correspondingly, the total sensing area of the sensing system 10 is the sum of the sensing areas of the respective image sensors.

[0041] In one implementation, the total sensing area of the sensing system 10 may be an annular area centered on the first vehicle. In this way, it is possible to ensure more comprehensive collection of environmental data around the first vehicle.

[0042] Figure 2A It is a schematic diagram of the total sensing area of the sensing system provided by an exemplary embodiment of the present disclosure.

[0043] As Figure 2A shown, the total sensing area of the sensing system 10 is an annular area 22 centered on the first vehicle 21. The annular area 22 may include the sensing areas of the respective image sensors. Taking the example that there are four image sensors provided on the first vehicle 21, namely a first image sensor provided at the head of the first vehicle 21, a second image sensor provided at the tail of the first vehicle 21, a third image sensor provided on the left side of the first vehicle 21, and a fourth image sensor provided on the right side of the first vehicle 21, and the sensing area of each image sensor is a sector centered on the first vehicle 21, the annular area 22 includes the sensing areas corresponding to the four image sensors, such as the sensing area 23-1 of the first image sensor, the sensing area 23-2 of the second image sensor, the sensing area 23-3 of the third image sensor, and the sensing area 23-4 of the fourth image sensor.

[0044] In one implementation, the decision-making system 20 may include one or more processors 201. The processor 201 may include a general-purpose processor, such as a central processing unit (CPU), a graphics processing unit (GPU), etc., or may also include an acceleration computing unit designed for deep learning tasks, autonomous driving tasks, etc., such as a neural processing unit (NPU), etc.

[0045] In one implementation, the decision-making system 20 may further include one or more memories 202. Program instructions executable by the processor 201 may be stored in the memory 202, and the processor 201 may load and execute the program instructions in the memory 202 to implement the functions of the decision-making system 20.

[0046] In addition, the memory 202 can also be used to cache or store intermediate data or result data generated by the processor 201 during operation, as well as store system files, application files, data files, etc. Exemplarily, the memory 202 can store environmental data, user instructions, etc. collected by the sensing system 10.

[0047] Exemplarily, the memory 202 can include, for example, volatile memory, such as dynamic random access memory (DRAM), static random access memory (SRAM), etc.; it can also include non-volatile memory (NVM), such as read-only memory (ROM), flash memory, etc.

[0048] In one implementation, the driving control system 30 can include one or more electronic control units (ECUs), etc. The driving control system 30 can execute the instructions of the decision-making system 20 through the one or more ECUs.

[0049] In one implementation, the decision-making system 20 can interact with the sensing system 10 to obtain environmental data (such as images and videos around the first vehicle) collected by the sensing system 10, and identify the second vehicle around the first vehicle based on the environmental data. When the decision-making system 20 identifies that the second vehicle meets the requirements, it generates an avoidance instruction, and based on the avoidance instruction, plans a driving path that can avoid the second vehicle that meets the requirements, and sends the avoidance instruction and the planned driving path to the driving control system 30. The driving control system 30 can control the first vehicle to drive according to the planned driving path based on the avoidance instruction, so as to specifically avoid the second vehicle that meets the requirements.

[0050] In one implementation, the vehicle avoidance system can also include a communication system 40, and the decision-making system 20 is communicatively connected to the communication system 40. The decision-making system 20 can upload data (such as collected environmental data, recognized vehicle images, etc.) to the server through the communication system 40, or receive data from the server through the communication system 40 (such as vehicle information of the second vehicle recognized by the server based on the environmental data, vehicle images, etc. uploaded by the first vehicle).

[0051] In one implementation, the vehicle avoidance system may further include an interaction system 50, and the decision-making system 20 is communicatively connected to the interaction system 50. The interaction system 50 is used to interact with the user, such as receiving various instructions from the user. Exemplarily, the interaction system 50 may include a touch screen, buttons, a microphone, an external device interface, etc. In this way, the interaction system 50 can receive instructions input by the user in different ways. For example, the interaction system 50 can receive gesture instructions from the user through the touch screen, receive button instructions from the user through the buttons, receive voice instructions from the user through the microphone, access the user device (such as a mobile phone, a tablet computer, a smart wearable device, etc.) through the external device interface, and receive instructions input by the user through the user device.

[0052] The solutions involved in this disclosure are not limited to the above-mentioned embodiments.

[0053] Exemplary Method

[0054] Figure 3 is a flowchart of a method for planning a vehicle driving path provided by an exemplary embodiment of the present disclosure.

[0055] Next, in conjunction with Figure 3 , each step of this method will be described by way of example.

[0056] In one embodiment, the method may include the following steps:

[0057] Step S100, determine at least one second vehicle within a preset range from the first vehicle.

[0058] The preset range is an area centered on the first vehicle and at a specified distance from the first vehicle. The vehicles appearing within the preset range are second vehicles, and the second vehicles are the vehicles that need to be further identified whether they need to be avoided.

[0059] Among them, the larger the preset range, the more likely it is that vehicles even at a relatively far distance from the first vehicle may be vehicles that need to be avoided; the smaller the preset range, the more likely it is that vehicles relatively close to the first vehicle are vehicles that may need to be avoided, and vehicles relatively far from the first vehicle are not vehicles that need to be additionally avoided.

[0060] It can be understood that the smaller the preset range, the fewer second vehicles participating in the subsequent identification, which is more conducive to reducing the calculation amount.

[0061] Figure 2B is a schematic diagram of the preset range provided by an exemplary embodiment of the present disclosure. In Figure 2B the largest circular area centered on the first vehicle 21 corresponds to the circular area 22 in Figure 2A In Figure 2BAmong the four sector regions obtained by dividing the maximum circular region centered on the first vehicle 21, they respectively correspond to Figure 2A the sensing regions of the four image sensors in

[0062] In the first implementation manner, the preset range can be the total sensing region of the sensing system 10. As Figure 2B shown, the preset range is the maximum circular region centered on the first vehicle 21. Since the second vehicle 24-1, the second vehicle 24-2, and the second vehicle 24-3 all appear within the preset range, therefore, at least one second vehicle within the preset range from the first vehicle 21 can be recognized, including the second vehicle 24-1, the second vehicle 24-2, and the second vehicle 24-3.

[0063] In the second implementation manner, the preset range can be a partial region within the total sensing region of the sensing system 10. For example, the preset range can be a partial region centered on the first vehicle within the total sensing region of the sensing system 10. That is to say, the preset range is smaller than the total sensing region of the sensing system 10.

[0064] In an example, the preset range can be a sub-circular region centered on the first vehicle within the total sensing region of the sensing system 10. Specifically, if the distance from the first vehicle to the boundary of the total sensing region is the first distance, and the distance from the first vehicle to the boundary of this sub-circular region is the second distance, and the second distance is less than the first distance. It can be referred to Figure 2B that the preset range is the sub-circular region 25 centered on the first vehicle 21 ( Figure 2B the shaded part in). Since the second vehicle 24-1 and the second vehicle 24-2 both appear within the sub-circular region 25, while the second vehicle 24-3 does not appear within the sub-circular region 25, therefore, at least one second vehicle within the preset range from the first vehicle 21 can be recognized, including the second vehicle 24-1 and the second vehicle 24-2.

[0065] In another example, the preset range can be a sector region corresponding to the sensing region of the image sensor within the sub-circular region centered on the first vehicle. It can be referred to Figure 2B that the preset range is the sector region 26 corresponding to the sensing region 23-1 of the first image sensor within the sub-circular region 25. Since the second vehicle 24-1 appears within the sector region 26, while the second vehicle 24-2 and the second vehicle 24-3 do not appear within the sector region 26, therefore, it can be determined that at least one second vehicle within the preset range from the first vehicle 21 only includes the second vehicle 24-1.

[0066] Step S200, determine the vehicle type of at least one second vehicle.

[0067] The vehicle type of the second vehicle is used to determine whether the corresponding second vehicle corresponds to a preset type that needs to be avoided.

[0068] In one implementation, vehicle types can be divided according to vehicle characteristics. Among them, vehicle characteristics can include at least one of price, type, color, model, shape, and brand. Exemplarily, vehicle types divided according to price can include high-price vehicles and low-price vehicles; vehicle types divided according to type can include special vehicles and non-special vehicles.

[0069] Step S300: Determine the first duration for which at least one second vehicle appears within the preset range.

[0070] It can be understood that the second vehicles may include vehicles passing by the first vehicle. These second vehicles pose a lower threat, that is, no special avoidance is required. For example, second vehicles in a stationary state, second vehicles with a relatively faster or slower speed relative to the first vehicle, second vehicles whose driving trajectory changes (such as driving out of the preset range), etc. Usually, these second vehicles passing by the first vehicle will drive out of the preset range shortly after entering the preset range. Therefore, the first duration for which the second vehicle appears within the preset range can be used to identify whether the second vehicle is a vehicle passing by the first vehicle. That is to say, the longer the first duration for which the second vehicle appears within the preset range, the longer the second vehicle drives around the first vehicle, and the second vehicle is a vehicle that drives around the first vehicle for a long time rather than passing by; the shorter the first duration for which the second vehicle appears within the preset range, the shorter the second vehicle drives around the first vehicle, and the second vehicle is a vehicle that passes by the first vehicle within a short time.

[0071] Step S400: Generate an avoidance instruction based on the vehicle type and the first duration.

[0072] The decision-making system 20 can comprehensively consider the vehicle type of the second vehicle and the first duration for which it appears within the preset range to determine whether the second vehicle is a vehicle that needs to be avoided. When the second vehicle is determined to be a vehicle that needs to be avoided, an avoidance instruction indicating to avoid the second vehicle is generated in a targeted manner, so as to accurately avoid the second vehicle. When the second vehicle is determined not to be a vehicle that needs to be avoided, an avoidance instruction indicating to avoid the second vehicle is not generated to avoid frequent avoidance of the first vehicle.

[0073] In one implementation, if the vehicle type of the second vehicle belongs to the vehicle types that need to be avoided (i.e., the preset types), and the first duration that the second vehicle appears within the preset range is greater than or equal to the preset time threshold, it can be determined that the second vehicle is a vehicle that needs to be avoided. If the vehicle type of the second vehicle does not belong to the vehicle types that need to be avoided (i.e., the preset types), and / or the first duration that the second vehicle appears within the preset range is less than the preset time threshold, it can be determined that the second vehicle is a vehicle that does not need to be avoided.

[0074] Step S500, plan the driving path of the first vehicle based on the avoidance instruction.

[0075] The decision-making system 20 plans the driving path of the first vehicle based on the avoidance instruction, and the planned driving path can specifically avoid the second vehicle that needs to be avoided.

[0076] In some cases, the planned driving path can be a driving path different from the current driving path, and the driving speed of the first vehicle can remain unchanged. In this way, by changing the driving path, the first vehicle can effectively avoid the second vehicle that needs to be avoided.

[0077] In some cases, the planned driving path can be the same as the current driving path, however, the driving speed of the first vehicle changes. For example, it reduces the driving speed or increases the driving speed. In this way, the first vehicle can avoid the second vehicle that needs to be avoided by adjusting the driving speed while maintaining the current driving path.

[0078] The decision-making system 20 transmits the planned driving path to the driving control system 30, and the driving control system 30 controls the first vehicle to drive according to the planned driving path, so as to effectively avoid the second vehicle that needs to be avoided.

[0079] In one example, if the preset type that needs to be avoided is a high-value vehicle (such as a unit price higher than or equal to 500,000 yuan), when it is determined that the vehicle type of the second vehicle is a high-value vehicle and the first duration that the second vehicle appears within the preset range is greater than or equal to the preset time threshold, an avoidance instruction can be generated to control the first vehicle to avoid the second vehicle in time, so as to achieve the purpose of avoiding high-value vehicles in time.

[0080] In another example, if the preset type that needs to be avoided is a special vehicle (such as an ambulance, a fire truck, a police car, a school bus, etc.), when it is determined that the vehicle type of the second vehicle is a special vehicle and the first duration that the second vehicle appears within the preset range is greater than or equal to the preset time threshold, an avoidance instruction can be generated to control the first vehicle to avoid the second vehicle in time, so as to achieve the purpose of avoiding special vehicles in time.

[0081] In yet another example, if the preset types of vehicles that need to be avoided include high - value vehicles and special - type vehicles, when it is determined that the vehicle type of the second vehicle is a high - value vehicle or a special - type vehicle, and the first duration during which the second vehicle appears within the preset range is greater than or equal to the preset time threshold, an avoidance instruction can be generated to control the first vehicle to avoid the second vehicle in a timely manner, so as to achieve the purpose of timely avoiding high - value vehicles and special - type vehicles. That is to say, the first vehicle can not only avoid a single type of vehicle targeted, but can avoid multiple types of vehicles targeted.

[0082] As can be seen from the above technical solutions, the method provided by the embodiments of the present disclosure can accurately screen out the second vehicles of the preset type that continuously appear within the preset range around the first vehicle and are greater than or equal to the preset time threshold from the second vehicles that appear around the first vehicle, and re - plan the driving route based on the second vehicle. Thus, it can not only avoid the second vehicles of the preset type targeted, but also avoid frequent avoidance.

[0083] Figure 4 It is a flowchart of a method for planning a vehicle driving route provided by another exemplary embodiment of the present disclosure.

[0084] As Figure 4 shown, in one implementation, step S100 may include the following steps:

[0085] Step S110, determine the vehicle state of the first vehicle.

[0086] The vehicle state includes a driving state and a parking state.

[0087] In some examples, the decision - making system 20 may send a request to obtain the vehicle state to the driving control system 30, and determine the vehicle state of the first vehicle based on the result feedback by the driving control system 30.

[0088] Step S120, generate a collection instruction based on the vehicle state.

[0089] Among them, if the vehicle state is the driving state, a collection instruction is generated to control the perception system 10 to collect the surrounding environmental data.

[0090] If the vehicle state is the parking state, no collection instruction is generated. That is to say, there is no need for the perception system 10 to collect the surrounding environmental data.

[0091] Thus, the surrounding environmental data can be collected targeted in the driving state, and the surrounding environmental data is not collected in the parking state, thereby reducing the power consumption generated in the parking state.

[0092] Step S130, collect the first image around the first vehicle based on the collection instruction.

[0093] The perception system 10 (such as an image sensor), based on the acquisition instruction, can collect the environmental data around the first vehicle and further obtain a first image from the environmental data. Among them, the acquisition range of the environmental data corresponds to the total perception area. The collected environmental data can be a first video or a first image sequence, where the first video and the first image sequence include images of the environment around the first vehicle. Correspondingly, the first image is a video frame in the first video or an image frame in the first image sequence.

[0094] In one example, the perception system 10 can collect the image data corresponding to the environmental information around the first vehicle at a preset time interval to obtain a first image sequence, and this first image sequence is the collected environmental data, and the first image is each frame image in this first image sequence.

[0095] In another example, the perception system 10 can collect the video data corresponding to the environmental information around the first vehicle to obtain a first video, and this first video is the collected environmental data, and the first image is each frame video in this first video.

[0096] Step S140: Determine a second image within a preset range of distance from the first vehicle from the first image.

[0097] The perception system 10 transmits the collected environmental data (such as the first video or the first image sequence) to the decision-making system 20, and the decision-making system 20 identifies the first image therein to determine a second image within a preset range of distance from the first vehicle in the first image.

[0098] In one implementation, the decision-making system 20 can identify the image content corresponding to the preset range in the first image.

[0099] In one example, the decision-making system 20 can crop the image content corresponding to the preset range from the first image based on the proportional relationship between the preset range and the total perception area of the perception system 10 as the second image. For example, crop the image content corresponding to Figure 2B the sub-annular region 25 in and use it as the second image.

[0100] Step S150: Determine at least one second vehicle based on the vehicle image included in the second image.

[0101] The decision-making system 20 can identify the image content in the second image to identify the vehicle image included in the second image, and this vehicle image is the image of the second vehicle that appears within a preset range of distance from the first vehicle. In this way, the decision-making system 20 can determine the second vehicle that appears within a preset range of distance from the first vehicle based on the identified vehicle image.

[0102] In one implementation, the decision-making system 20 stores the second image in the corresponding memory 202, and identifies the vehicle image in the second image through an algorithm module (such as a picture perception module) for identifying vehicle images. Among them, the processor 201 of the decision-making system 20 can call the picture perception module. When the picture perception module runs, it can call the second image in the memory 202 and identify the vehicle image from the second image.

[0103] Figure 5 It is a flowchart of a method for planning a vehicle driving path provided by another exemplary embodiment of the present disclosure.

[0104] As Figure 5 shown, in one implementation, step S200 may include the following steps:

[0105] Step S210, determining the vehicle image corresponding to at least one second vehicle from the second image.

[0106] In one implementation, the decision-making system 20 adds a vehicle identifier to the vehicle image. Among them, different vehicle identifiers are added to the vehicle images corresponding to different second vehicles. In this way, the decision-making system 20 can accurately determine the vehicle images corresponding to the same second vehicle included in the second images of consecutive frames based on the vehicle identifier, which is beneficial to accurately calculating the first duration when the second vehicle appears within the preset range subsequently.

[0107] Among them, when the vehicle images corresponding to the second vehicle are included in two adjacent frames of the second image, the decision-making system 20 can match the vehicle images in the two adjacent frames of the second image to determine whether the vehicle images in the two adjacent frames of the second image correspond to the same second vehicle. If so, the decision-making system 20 adds the same vehicle identifier to the vehicle images corresponding to the same second vehicle in the two adjacent frames of the second image. Among them, the vehicle identifier can be, for example, a vehicle tracking identifier (track ID).

[0108] Exemplarily, the decision-making system 20 matching the vehicle images in two adjacent frames of the second image may include: respectively selecting a frame of vehicle image from two adjacent frames of the second image, and calculating the intersection over union (IoU) of the two selected frames of vehicle images. If the IoU is greater than or equal to a preset threshold, it can be determined that the two frames of vehicle images correspond to the same second vehicle, and the same track ID can be added to the two frames of vehicle images; if the IoU is less than the preset threshold, it can be determined that the two frames of vehicle images correspond to different second vehicles.

[0109] Thus, the vehicle image corresponding to each second vehicle can be accurately identified from the second image.

[0110] Step S220: Determine the vehicle features of at least one second vehicle based on the vehicle images corresponding to at least one second vehicle.

[0111] To improve the accuracy of determining vehicle features, the vehicle images used to determine vehicle features can be screened in advance.

[0112] In one example, the vehicle images used to determine vehicle features can be at least one vehicle image with a clarity higher than the clarity threshold among the frames of vehicle images obtained by the decision-making system 20.

[0113] In one example, the vehicle images used to determine vehicle features can be at least one vehicle image with a relatively high integrity of image information among the frames of vehicle images obtained by the decision-making system 20, such as vehicle images with less occlusion and better shooting angles.

[0114] In one implementation, the decision-making system 20 can determine the vehicle features of the second vehicle based on the vehicle images corresponding to the second vehicle.

[0115] In one example, the decision-making system 20 stores the second image to be recognized in the memory 202. The second image to be recognized includes the vehicle images used to determine vehicle features. The decision-making system 20 recognizes the vehicle features included in the vehicle images through an algorithm module for recognizing vehicle features (such as a feature recognition module). Among them, the processor 201 of the decision-making system 20 can call the feature recognition module. When the feature recognition module runs, it can call the second image to be recognized in the memory 202 and determine the vehicle features of the second vehicle based on the vehicle images in the second image to be recognized.

[0116] In another implementation, a neural network model can be used to perform feature recognition on the vehicle images to determine the vehicle features of the second vehicle. Among them, the decision-making system 20 can input the vehicle images into the neural network model, and the neural network model outputs the vehicle features of the second vehicle.

[0117] In one example, the program code of the neural network model can be stored in the memory 202 of the decision-making system 20. The CPU of the decision-making system 20 can call the NPU to run the neural network model to perform the task of feature recognition on the vehicle images.

[0118] In another example, the neural network model can be provided by a cloud server, such as a multi-modal large model. Correspondingly, the cloud server performs the task of feature recognition on the vehicle images. The decision-making system 20 needs to be pre-configured with prompt information for obtaining vehicle features, and the specific content of the prompt information matches the preset types that need to be avoided.

[0119] For example, if the preset type to be avoided is a high - price vehicle, correspondingly, the feature for classifying vehicle types is price, and the prompt message can be configured as "How much is this vehicle?"

[0120] Another example, if the preset type to be avoided is a special vehicle, correspondingly, the feature for classifying vehicle types is type, and the prompt message can be configured as "What is the use of this vehicle?"

[0121] It should be noted that the specific content of the prompt message pre - configured in the decision - making system 20 can be flexibly configured according to actual requirements (such as the preset type to be actually avoided), and no specific restrictions are imposed on this.

[0122] After the decision - making system 20 obtains the vehicle image, it can transmit the vehicle image and the pre - configured prompt message to the cloud server through the communication system 40. Then the cloud server inputs the vehicle image and the prompt message into the neural network model to output the vehicle features of the second vehicle for each prompt message through the neural network model, and then the cloud server feeds back the vehicle features of the second vehicle to the decision - making system 20.

[0123] In this way, the cloud server can share the task of feature recognition for the vehicle image to reduce the computing pressure on the decision - making system 20. At the same time, since the decision - making system 20 does not need to execute the task of feature recognition for the vehicle image, the decision - making system 20 does not need to be configured with the corresponding neural network model, thereby reducing the cost of the decision - making system 20.

[0124] Step S230: Determine the vehicle types of at least one second vehicle based on the vehicle features of at least one second vehicle.

[0125] There is a corresponding relationship between vehicle types and feature ranges. After determining the vehicle features of the second vehicle, the feature range to which the vehicle features belong can be determined. Furthermore, based on the belonging feature range and the corresponding relationship, the vehicle type corresponding to the second vehicle can be determined.

[0126] Exemplarily, there is a corresponding relationship between vehicle types and price ranges. For example, vehicle types can include high - price vehicles and non - high - price vehicles. Among them, high - price vehicles correspond to the price range where the price is greater than or equal to the price threshold; low - price vehicles correspond to the price range where the price is less than the price threshold. After identifying the price of the second vehicle, the price range to which the price of the second vehicle belongs can be determined, and then based on the corresponding relationship, the vehicle type of the second vehicle can be determined.

[0127] Exemplarily, there is a corresponding relationship between vehicle types and category ranges. For example, vehicle types may include special vehicles and non-special vehicles. Among them, special vehicles correspond to a first category range, and the first category range includes a first category (such as fire trucks, ambulances, police cars, etc.); non-special vehicles correspond to a second category range, and the second category range includes a second category, which is different from the first category.

[0128] Figure 6 It is a flowchart of a method for planning a vehicle driving path provided by another exemplary embodiment of the present disclosure.

[0129] As Figure 6 shown, in one implementation, step S300 may include the following steps:

[0130] Step S310, determining a vehicle image corresponding to at least one second vehicle from a second image.

[0131] Step S310 is similar to step S210, and will not be elaborated here.

[0132] Step S320, determining the number of consecutive frames of the vehicle image corresponding to at least one second vehicle.

[0133] For each second vehicle, determine the number of consecutive frames of its corresponding vehicle image.

[0134] Exemplarily, as described in step S210, determine a vehicle image corresponding to at least one second vehicle from a second image, and mark the same track ID for the vehicle images corresponding to the same second vehicle. Thus, when determining the number of consecutive frames of the vehicle image corresponding to a certain second vehicle v1, the consecutive vehicle images with the track ID corresponding to the second vehicle v1 in the second image can be identified, and by accumulating the number of frames of these consecutive vehicle images, the number of consecutive frames of the vehicle image corresponding to the second vehicle v1 is obtained.

[0135] In one implementation, if the vehicle image of the second vehicle is not recognized in the second image, the statistics of the number of consecutive frames of the vehicle image corresponding to the second vehicle are terminated, that is, the current round of statistics of the first duration of the second vehicle appearing within the preset range is terminated. That is to say, the first duration is the duration that the second vehicle continuously appears within the preset range.

[0136] In an example, the decision-making system 20 may count the number of frames as 1 when the vehicle image of any second vehicle v1 is first recognized, and add 1 to the count every time a frame of the vehicle image of the second vehicle v1 is recognized later. During the counting process, once the vehicle image of the second vehicle v1 is not recognized, the counting is terminated, and the current count is determined as the number of consecutive frames of the vehicle image corresponding to the second vehicle v1.

[0137] Step S330: Determine the first duration for at least one second vehicle to appear within the preset range based on the number of frames of the vehicle images corresponding to at least one second vehicle and the time interval between two adjacent frames of the vehicle images corresponding to at least one second vehicle.

[0138] The first duration for the second vehicle to appear within the preset range is the duration from obtaining the first frame of the vehicle image to obtaining the latest frame of the vehicle image. That is, the sum of the time intervals between two adjacent frames of the vehicle images from the first frame to the latest frame.

[0139] Taking the time interval between two adjacent frames of the vehicle images as the same for example, following the example in step S320, the decision-making system 20 can calculate the first duration for the second vehicle v1 to appear within the preset range based on formula (1):

[0140] T = t×(i - 1) (1)

[0141] Where, T represents the first duration for the second vehicle v1 to appear within the preset range, t represents the time interval between two adjacent frames of the vehicle images, and i represents the consecutive number of frames of the vehicle images corresponding to the second vehicle v1 (the current count).

[0142] In another implementation, if no vehicle image of the second vehicle is recognized in the second image, terminate the counting of the consecutive number of frames of the vehicle images corresponding to the second vehicle to obtain the first count. At this time, do not terminate the current round of counting of the first duration for the second vehicle to appear within the preset range. Start timing the second duration, and based on the second duration and the recognition result of the vehicle images of the second vehicle within the preset time interval, count the first duration for the second vehicle to appear within the preset range, where the second duration is the duration starting from when no vehicle image of the second vehicle is recognized, and the preset time interval is the maximum time interval from when no vehicle image of the second vehicle is recognized to when the vehicle image of the second vehicle is recognized again.

[0143] Where, if the recognition result is that the vehicle image of the second vehicle is recognized again within the preset time interval, start counting the consecutive number of frames of the vehicle images corresponding to the second vehicle again to obtain the second count. Based on the first count, the second duration, and the second count, determine the first duration for the second vehicle to appear within the preset range. Wherein, the process of determining the duration for the second vehicle to appear within the preset range according to the first count, and the process of determining the duration for the second vehicle to appear within the preset range according to the second count, can refer to step S330 and will not be elaborated here. Add the duration calculated based on the first count, the second duration, and the duration calculated based on the second count together, and the first duration for the second vehicle to appear within the preset range can be obtained.

[0144] If the recognition result is that the vehicle image of the second vehicle is not recognized again within a preset time interval, terminate the current round of statistics on the first duration of the second vehicle appearing within the preset range. Determine the first duration of the second vehicle appearing within the preset range based on the first count.

[0145] In some cases, if, after restarting the statistics on the consecutive number of frames of the vehicle image corresponding to the second vehicle, the situation where the vehicle image corresponding to the second vehicle is not recognized appears again, repeat the process of starting the timing of the second duration and, based on the second duration and the recognition result of the vehicle image of the second vehicle within the preset time interval, statistically calculate the first duration of the second vehicle appearing within the preset range until the current round of statistics on the first duration of the second vehicle appearing within the preset range is terminated. In these cases, the first duration of the second vehicle appearing within the preset range is equal to the sum of the duration calculated based on the count of the consecutive number of frames of each statistical calculation and each segment of the second duration.

[0146] Based on the above process, if the second vehicle briefly drives out of the preset range and then appears within the preset range again, that is, the second vehicle reciprocates within the preset range, when the first duration of the second vehicle reciprocating within the preset range meets the preset time threshold, it also meets the duration requirement for avoidance.

[0147] Compared with the second vehicle continuously appearing within the preset range, the second vehicle reciprocating within the preset range can be considered to have a worse driving route stability. Based on this, the second vehicle reciprocating within the preset range can be set as the second vehicle with a higher avoidance priority. Further, it can be set that the more times the vehicle reciprocates within the preset range, the higher the corresponding avoidance priority. That is to say, if multiple second vehicles that need to be avoided are recognized, in the case where these second vehicles include the second vehicle reciprocating within the preset range, give priority to avoiding the second vehicle reciprocating within the preset range; in the case where these second vehicles include multiple second vehicles reciprocating within the preset range, give priority to avoiding the second vehicle with more reciprocating times. Based on this, the first vehicle can more specifically avoid the second vehicle with an unstable driving route and a higher threat to the vehicle itself.

[0148] In some embodiments, after determining the vehicle type of at least one second vehicle, the first duration of at least one second vehicle appearing within the preset range can be determined.

[0149] In some other embodiments, after determining the first duration of at least one second vehicle appearing within the preset range, the vehicle type of at least one second vehicle can be determined.

[0150] Figure 7It is a flowchart of a method for planning a vehicle driving route provided by another exemplary embodiment of the present disclosure.

[0151] As Figure 7 shown, in one implementation, step S400 may include the following steps:

[0152] Step S410, determining the matching relationship between the vehicle type and the preset type.

[0153] The preset type is the vehicle type that needs to be avoided.

[0154] In one implementation, the preset type is the vehicle type preset before the first vehicle is in a driving state. Among them, the preset type can be the default set vehicle type or the vehicle type set by the user.

[0155] In an example, when the first vehicle is in a parked state, the user can set the preset type through the interaction system 50. Taking the user setting the preset type through the touch screen in the interaction system 50 as an example, as Figure 8 shown, before the first vehicle travels, the user can open the setting menu through the touch screen in the interaction system 50, as Figure 8 shown in ①. This setting menu may include options for vehicle types, such as the option for high - price vehicles and the option for special vehicles. If the preset type that the user wants to set is a high - price vehicle, the user can perform a click operation A on the price option. As Figure 8 shown in ②, the interaction system 50 can respond to the click operation A and display a price setting page. This price setting page may include a price input box, and the user can enter the price threshold for dividing vehicle types in this price input box. As Figure 8 shown in ②, taking the price threshold that the user wants to set as 200,000 yuan as an example, the user can enter, for example, 20 in the price input box. The interaction system 50 will transmit the preset type set by the user (that is, the high - price vehicle) and the price threshold corresponding to this preset type (that is, 200,000 yuan) to the decision - making system 20. The decision - making system 20 sets the preset type based on the high - price vehicle and the price threshold set by the user (that is, 200,000 yuan), that is, the preset type is a high - price vehicle, and the price range corresponding to the high - price vehicle is a price greater than or equal to 200,000 yuan.

[0156] In another implementation, the preset type is the vehicle type set by the user in real - time when the first vehicle is in a driving state.

[0157] In an example, when the first vehicle is in a driving state, the user can set the preset type in real - time through the exchange system 50. For example, the user can set the preset type in real - time through voice.

[0158] After determining the vehicle types of the second vehicles, the decision-making system 20 can determine the matching relationship between them by comparing the vehicle types of the second vehicles with the preset types.

[0159] If the matching relationship is that the vehicle type of the second vehicle belongs to the preset type, that is, they match, it indicates that the corresponding second vehicle may be a vehicle that needs to be avoided; if the matching relationship is that the vehicle type of the second vehicle does not belong to the preset type, that is, they do not match, it indicates that the corresponding second vehicle is not a vehicle that needs to be avoided.

[0160] Step S420, determine the magnitude relationship between the first duration and the duration threshold.

[0161] Among them, if the first duration is greater than or equal to the duration threshold, it indicates that the duration for which the corresponding second vehicle appears within the preset range meets the duration requirement for the vehicle that needs to be avoided, and this second vehicle may be a vehicle that needs to be avoided; if the first duration is less than the duration threshold, it indicates that the duration for which the corresponding second vehicle appears within the preset range does not meet the duration requirement for the vehicle that needs to be avoided, and this second vehicle is not a vehicle that needs to be avoided.

[0162] Step S430, generate an avoidance instruction based on the matching relationship between the vehicle type of the second vehicle and the preset type and the magnitude relationship between the first duration and the duration threshold.

[0163] The second vehicle to be avoided needs to meet the requirements for both the preset type and the duration threshold simultaneously.

[0164] Among them, if the vehicle type of the second vehicle matches the preset type and the first duration is greater than or equal to the duration threshold, it indicates that this second vehicle meets the requirements for both the preset type and the duration threshold simultaneously and is a vehicle that needs to be avoided. Therefore, an avoidance instruction is generated, and this avoidance instruction is used to indicate avoiding this second vehicle; if the vehicle type of the second vehicle does not match the preset type, and / or the first duration is less than the duration threshold, it indicates that this second vehicle does not meet the requirements for both the preset type and the duration threshold simultaneously and is a vehicle that does not need to be avoided. Therefore, no avoidance instruction is generated.

[0165] Thus, based on the avoidance instruction, the first vehicle can be accurately controlled to avoid the second vehicle that appears around it and belongs to the preset type and exceeds the preset time threshold.

[0166] Figure 9 It is a flowchart of a method for real-time setting of a preset type provided by an exemplary embodiment of the present disclosure.

[0167] As Figure 9 shown, in one implementation, before step S410, the following steps are further included:

[0168] Step S440, collect the first voice of the user.

[0169] The user can input the first voice through the interactive system 50 at any time during the driving process of the first vehicle, that is, when the first vehicle is in the driving state, so as to issue instructions to the vehicle avoidance system in the form of voice.

[0170] Step S450: determining the first type specified by the user and the timeliness information of the first type based on the first voice.

[0171] The first type is a preset type that the user wants to set, that is, the type of vehicle that the user wants the first vehicle to avoid.

[0172] In one implementation, the first type in the first speech may be determined by using automatic speech recognition (ASR) technology and natural language processing (NLP) technology.

[0173] In one example, the user can input a first voice through the microphone of the interactive system 50. The first voice input by the user needs to contain the first type to be set. For example, if the user wants the first vehicle to avoid a large vehicle, the user can input the first voice "I want to avoid a large vehicle". The interactive system 50 transmits the first voice to the decision system 20. The decision system 20 can convert the first voice into a corresponding text through a voice recognition system, and then parse the text through a natural language processing system to determine the intention corresponding to the text, and then determine the first type specified by the user, such as "large vehicle". It can be seen that during the driving process of the first vehicle, the user sets the first type of temporary avoidance by inputting voice, without having to set the first type by interacting with the interactive system 50 with both hands, so that there is no need to occupy both hands, and more energy can be focused on driving operations, making the driving process safer.

[0174] The first type specified by the user may be considered as a type of vehicle to be temporarily avoided, and therefore the first type also has corresponding validity information, which includes the requirement that the first type is valid as a preset type.

[0175] In one implementation, the user can set the first type of timeliness information by using the first voice when setting the first type. For example, the first voice spoken by the user includes keywords related to timeliness information. Among them, the keywords related to timeliness information may include "always", "always", "this time", "single time", etc. Accordingly, the decision system 20 can determine the timeliness information based on the keywords in the first voice.

[0176] In one example, the user says the first voice "always avoid large vehicles", and the decision-making system 20 can recognize a keyword (such as "always") from the first voice, and can determine the time-limited information based on this keyword as: the first type is valid as a preset type from the time when the decision-making system 20 obtains the first voice to the end of the current driving process of the first vehicle.

[0177] In another example, the user says the first voice "avoid large vehicles this time", and the decision-making system 20 can recognize a keyword (such as "this time") from the first voice, and can determine the time-limited information based on this keyword as: the first type is valid as a preset type from the time when the decision-making system 20 obtains the first voice to the end of one avoidance action performed by the first vehicle.

[0178] Step S460, generate a setting instruction based on the first type and the time-limited information of the first type.

[0179] After the interaction system 50 determines the first type and the time-limited information of the first type, it generates a corresponding setting instruction, which instructs to set the first type as a preset type, and sets the requirements for the first type to be valid as a preset type according to the time-limited information.

[0180] The interaction system 50 transmits the setting instruction to the decision-making system 20.

[0181] Step S470, set the preset type based on the setting instruction.

[0182] The decision-making system 20 sets the first type as a preset type based on the setting instruction, and monitors the validity of the first type as a preset type according to the requirements for the first type to be valid as a preset type.

[0183] In one example, the decision-making system 20 can store the first type in the memory 202. The memory 202 can store a relevant list of vehicle types set as preset types, and the decision-making system 20 can manage the preset types by writing or deleting vehicle types in this list.

[0184] Figure 10 It is a flowchart of a method for determining the matching relationship between a vehicle type and a preset type provided by an exemplary embodiment of the present disclosure.

[0185] As Figure 10 shown, in one implementation, step S410 includes the following steps:

[0186] Step S411, determine the target type that is valid in the state during the process of planning the vehicle driving path in the preset type.

[0187] The target type that is valid in the state during the process of planning the vehicle driving path in the preset type, that is, the vehicle type that needs to be avoided.

[0188] If the preset types include vehicle types that are preset before the first vehicle is in a driving state (for the sake of convenience of description, these vehicle types are referred to as "second types"), it can be determined that the second types are vehicle types that are always valid during the process of planning the vehicle driving path, that is, it can be directly determined that the second types are the target types.

[0189] If the preset types include the first types that are set in real time by the user when the first vehicle is in a driving state, the state of the first types during the process of planning the vehicle driving path can be determined based on the timeliness information of the first types. If it is determined that the first types are valid based on the timeliness information of the first types, it can be determined that the first types are the target types; if it is determined that the first types are invalid based on the timeliness information of the first types, it can be determined that the first types are not the target types.

[0190] Step S412, determine the matching priority of the target types.

[0191] The matching priority of the target types refers to the priority of retaining the matching relationships, where the second vehicle with the retained matching relationship is the second vehicle determined to need to be further judged whether it needs to be avoided, and the second vehicle without the retained matching relationship is the second vehicle determined not to need to be avoided.

[0192] Specifically, when the matching relationships between the vehicle types of multiple second vehicles and different target types are all matched, if the matching priorities of the different target types are equal, all the matching relationships are retained, that is, the matching relationships corresponding to these multiple second vehicles are all matched; if the matching priorities of the different target types are different, only the matching relationship where the vehicle type of the second vehicle is matched with the target type with a higher matching priority is retained, and the matching relationship where the vehicle type of the second vehicle is matched with the target type with a lower matching priority is not retained. That is, among these multiple second vehicles, the matching relationship corresponding to the second vehicle whose vehicle type is matched with the target type with a higher matching priority is matched, while the matching relationship corresponding to the second vehicle whose vehicle type is matched with the target type with a lower matching priority is not matched.

[0193] In an example, the matching priority of the first type in the target types is higher than that of the second type. That is to say, when there are multiple second vehicles whose vehicle types are respectively matched with the first type and the second type, the second vehicles whose vehicle types are matched with the second type are not avoided, and the second vehicles whose vehicle types are matched with the first type are avoided. Equivalently, at the stage of matching vehicle types, the second vehicles that do not need to be avoided are further screened out. On the one hand, it can more accurately avoid the second vehicles of the first type temporarily set by the user. On the other hand, it can also reduce the number of second vehicles that need to be judged whether to be avoided subsequently, thereby reducing the calculation amount.

[0194] Step S413: Determine the matching relationship between the vehicle type and the target type based on the matching priority.

[0195] Match the vehicle types of the second vehicles with the target type to preliminarily determine the corresponding matching relationships of the second vehicles. Based on the matching priority, further process the corresponding matching relationships of the second vehicles preliminarily determined to obtain the final corresponding matching relationships of the second vehicles.

[0196] Thus, in the vehicle type matching stage, the second vehicles that do not need to be avoided can be screened out first, and the second vehicles that better meet the requirements of the vehicle type to be avoided can be retained, so as to achieve more accurate avoidance and effectively reduce the calculation amount.

[0197] Figure 11 It is a flowchart of a method for planning a vehicle driving path provided by an exemplary embodiment of the present disclosure.

[0198] As Figure 11 shown, in one implementation, step S500 includes the following steps:

[0199] Step S510: If there are at least two second vehicles to be avoided, determine the avoidance priority corresponding to each second vehicle to be avoided based on the avoidance instruction.

[0200] The avoidance priority refers to the priority order of avoidance. Among them, the second vehicle with a higher avoidance priority is avoided first.

[0201] In the first implementation, the avoidance priority corresponding to the second vehicle can be determined based on the threat of the second vehicle to be avoided to the first vehicle. Among them, the greater the threat of the second vehicle to be avoided to the first vehicle, the higher the corresponding avoidance priority.

[0202] Combined with Figure 2B , if the second vehicles to be avoided include the second vehicle 24-1 and the second vehicle 24-2, the decision-making system 20 can respectively evaluate the threats of the second vehicle 24-1 and the second vehicle 24-2 to the first vehicle 21. For example, evaluate based on the appearance mode of the second vehicle 24-1 and the second vehicle 24-2 within a preset range. If the second vehicle 24-1 appears repeatedly within the preset range, while the second vehicle 24-2 appears continuously within the preset range, and the evaluation result is that the threat of the second vehicle 24-1 to the first vehicle 21 is greater, the decision-making system 20 can determine that the avoidance priority of the second vehicle 24-1 is higher than that of the second vehicle 24-2.

[0203] In the second implementation, if the vehicle types of the second vehicles to be avoided are the same, determine the avoidance priority corresponding to the second vehicle based on the vehicle characteristics related to the vehicle type.

[0204] In one example, if the vehicle types of the second vehicles to be avoided are all high - price vehicles, the corresponding avoidance priorities are determined based on the prices of the second vehicles. Among them, the higher the price of the second vehicle, the higher the corresponding avoidance priority; the lower the price of the second vehicle, the lower the corresponding avoidance priority.

[0205] Combined with Figure 2B , if the second vehicles to be avoided include the second vehicle 24 - 1 and the second vehicle 24 - 2, and both the second vehicle 24 - 1 and the second vehicle 24 - 2 are high - price vehicles, the decision - making system 20 can respectively obtain the prices of the second vehicle 24 - 1 and the second vehicle 24 - 2. For example, the price of the second vehicle 24 - 1 is 200,000 yuan, and the price of the second vehicle 24 - 2 is 250,000 yuan. The decision - making system 20 can determine that the price of the second vehicle 24 - 2 is higher, and then can determine that the avoidance priority of the second vehicle 24 - 2 is higher than that of the second vehicle 24 - 1.

[0206] In another example, if the vehicle types of the second vehicles to be avoided are all special vehicles, the corresponding avoidance priorities are determined based on the usage status of the second vehicles. Among them, when the usage status of the second vehicle is the working status, it corresponds to a high avoidance priority; when the usage status of the second vehicle is the idle status, it corresponds to a low avoidance priority.

[0207] Combined with Figure 2B , if the second vehicles to be avoided include the second vehicle 24 - 1 and the second vehicle 24 - 2, and both the second vehicle 24 - 1 and the second vehicle 24 - 2 are special vehicles, the usage statuses of the second vehicle 24 - 1 and the second vehicle 24 - 2 are respectively identified. For example, by detecting whether the second vehicle 24 - 1 and the second vehicle 24 - 2 play a specified sound, the usage statuses of the second vehicle 24 - 1 and the second vehicle 24 - 2 are identified. Taking the second vehicle 24 - 1 being in the working status and the second vehicle 24 - 2 being in the idle status as an example, the decision - making system 20 can determine that the avoidance priority of the second vehicle 24 - 1 is higher than that of the second vehicle 24 - 2.

[0208] In the third implementation, if the vehicle types of the second vehicles to be avoided are different, the corresponding avoidance priorities of the second vehicles are determined based on the number of target types matching the vehicle types of the second vehicles. Among them, the more the number of target types matching the vehicle type of the second vehicle, the higher the corresponding avoidance priority of the second vehicle; the fewer the number of target types matching the vehicle type of the second vehicle, the lower the corresponding avoidance priority of the second vehicle.

[0209] In one example, combined with Figure 2B, if the second vehicle to be avoided includes the second vehicle 24-1 and the second vehicle 24-2, and the second vehicle 24-1 is a high-value vehicle or a special vehicle, and the second vehicle 24-2 is a special vehicle, then the decision-making system 20 may determine that the number of target types matching the vehicle type of the second vehicle 24-1 is 2, and the number of target types matching the vehicle type of the second vehicle 24-2 is 1. Thus, it can be determined that the avoidance priority of the second vehicle 24-1 is higher than that of the second vehicle 24-2.

[0210] In the fourth implementation, if the vehicle types of the second vehicles to be avoided are different, based on the avoidance priorities of the vehicle types of the second vehicles, the corresponding avoidance priorities of the second vehicles are determined. Among them, the higher the avoidance priority of the vehicle type of the second vehicle, the higher the corresponding avoidance priority of the second vehicle; the lower the avoidance priority of the vehicle type of the second vehicle, the lower the corresponding avoidance priority of the second vehicle.

[0211] In an example, combined with Figure 2B , if the second vehicle to be avoided includes the second vehicle 24-1 and the second vehicle 24-2, and the second vehicle 24-1 is a high-value vehicle and the second vehicle 24-2 is a special vehicle, taking the avoidance priority of the special vehicle being higher than that of the high-value vehicle as an example, the decision-making system 20 may determine that the avoidance priority of the second vehicle 24-2 is higher than that of the second vehicle 24-1.

[0212] Step S520, based on the avoidance priorities corresponding to each second vehicle to be avoided, plan the driving path of the first vehicle.

[0213] After the decision-making system 20 determines the avoidance priorities corresponding to each second vehicle to be avoided, it may determine the second vehicle to be avoided with the highest corresponding avoidance priority as the target vehicle, and plan the driving path of the first vehicle for this target vehicle. The re-planned driving path can meet the requirement of giving priority to avoiding the target vehicle.

[0214] The solution involved in this disclosure is not limited to the above-mentioned embodiments.

[0215] Exemplary Device

[0216] The vehicle avoidance method provided by the embodiments of this disclosure is introduced above. It can be understood that in order to implement the various functions of this control method, the vehicle avoidance system may include corresponding hardware and software for implementing the hardware functions.

[0217] Those skilled in the art should easily realize that, in combination with the steps of a method for planning a vehicle driving path described in various embodiments of the present disclosure, the various embodiments of the present disclosure can be implemented in the form of hardware or in a combined form of software driving hardware. Whether a certain function is executed in the form of hardware or software driving hardware depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods for each specific application to implement the described function, but such implementation should not be considered to exceed the scope of the present disclosure.

[0218] Figure 12 FIG. 4 is a schematic structural diagram of a device for planning a vehicle driving path provided by an exemplary embodiment.

[0219] As Figure 12 shown, in one embodiment, the device for planning a vehicle driving path includes: a perception module 121, an identification module 122, a decision module 123, and a planning module 124.

[0220] Among them, the perception module 121 is used to determine at least one second vehicle within a preset range from the first vehicle.

[0221] The identification module 122 is used to determine the vehicle type of at least one second vehicle.

[0222] The identification module 122 is further used to determine the first duration for which at least one second vehicle appears within the preset range.

[0223] The decision module 123 is used to generate an avoidance instruction based on the vehicle type and the first duration.

[0224] The planning module 124 is used to plan the driving path of the first vehicle based on the avoidance instruction.

[0225] Thus, it is possible to accurately screen out second vehicles of a preset type that continuously appear within the preset range around the first vehicle for a duration greater than or equal to a preset time threshold, and re-plan the driving path based on the second vehicle. Therefore, not only can it specifically avoid second vehicles of a preset type, but also it can avoid frequent avoidance.

[0226] The solution involved in the present disclosure is not limited to the above-mentioned embodiments.

[0227] Exemplary Electronic Device

[0228] Figure 13 FIG. 5 is a structural diagram of an electronic device provided by the present disclosure. The electronic device 13 may include a processor 131, and the processor 131 may execute at least one program instruction to implement the method for planning a vehicle driving path provided by the embodiments of the present disclosure.

[0229] In one embodiment, the electronic device 13 may further include:

[0230] A memory 132, which may include an internal memory and an external memory.

[0231] A device interface 133, which is used to connect to an external device to enable communication between the electronic device 13 and the external device. The device interface 133 may include, for example, a controller area network (CAN) bus interface, a universal asynchronous receiver / transmitter (UART) interface, a media oriented systems Transport (MOST) bus interface, an in-vehicle Ethernet bus interface, a pulse per second (PPS) interface, a low-voltage differential signal ing (LVDS) interface, etc.

[0232] Among them, the external device may include an input device 134, an output device 135, an execution device 136, etc. of the first vehicle. Among them, the input device 134 includes, but is not limited to, at least one of the following: a camera, a lidar, a millimeter-wave radar, an ultrasonic sensor, a global navigation satellite system receiver, etc., a microphone, an in-cabin camera, a button, etc. The output device 135 includes, but is not limited to, at least one of the following: a digital instrument panel, a central control screen, a co-pilot screen, a head-up display, a speaker, etc. The execution device 136 may include, for example, at least one ECU, etc. The execution device 136 may execute instructions from the electronic device 13, such as an avoidance instruction, to perform driving control on the first vehicle, such as controlling the acceleration, deceleration, braking, steering, etc. of the first vehicle.

[0233] The solution involved in the present disclosure is not limited to the above-mentioned embodiments.

[0234] Exemplary Computer Program Product and Computer Readable Storage Medium

[0235] In addition to the above methods and devices, an embodiment of the present disclosure may also be a computer program product, which includes computer program instructions that, when run by a processor, cause the processor to execute the steps in the bandwidth control method according to various embodiments of the present disclosure described in the "Exemplary Method" section of this specification.

[0236] A computer program product may be written in any combination of one or more programming languages for programming code to perform the operations of the embodiments of the present disclosure. The programming languages include object-oriented programming languages such as Java, C++, etc., and also include conventional procedural programming languages such as the "C" language or similar programming languages. The programming code may be executed entirely on the user's computing device, partially on the user's device, executed as a stand-alone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0237] In addition, an embodiment of the present disclosure may also be a computer-readable storage medium having computer program instructions stored thereon, and when the computer program instructions are run by a processor, the processor is caused to execute the steps in the bandwidth control method according to various embodiments of the present disclosure described in the "Exemplary Method" section above of this specification.

[0238] The computer-readable storage medium may employ any combination of one or more readable media. The readable media may be a readable signal medium or a readable storage medium. The readable storage medium may, for example, include but is not limited to an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples (non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical memory device, a magnetic memory device, or any suitable combination of the above.

[0239] The solution involved in the present disclosure is not limited to the above-mentioned embodiments.

[0240] The basic principles of the present disclosure have been described above in conjunction with specific embodiments. However, the advantages, benefits, effects, etc. mentioned in the present disclosure are only examples and not limitations, and it cannot be considered that they are essential for each embodiment of the present disclosure. In addition, the above-mentioned specific details are only for the purpose of illustration and facilitating understanding, rather than limitations. The above details do not limit the present disclosure to necessarily adopt the above specific details for implementation.

[0241] Those skilled in the art can make various changes and modifications to the present disclosure without departing from the spirit and scope of the present disclosure. Thus, if these modifications and variations of the present disclosure fall within the scope of the claims of the present disclosure and their equivalent technologies, the present disclosure is also intended to include these changes and modifications.

Claims

1. A method for planning a driving route of a vehicle, comprising: Determining at least one second vehicle within a preset range from a first vehicle; Determining the vehicle type of the at least one second vehicle; Determining a first duration during which the at least one second vehicle appears within the preset range; Generating an avoidance instruction based on the vehicle type and the first duration; Planning the driving route of the first vehicle based on the avoidance instruction.

2. The method for planning a vehicle driving route according to claim 1, wherein, The determining at least one second vehicle within a preset range from a first vehicle includes: Determining the vehicle state of the first vehicle; Generating a collection instruction based on the vehicle state; Collecting a first image around the first vehicle based on the collection instruction; Determining a second image from the first image that is at the preset range from the first vehicle; Determining the at least one second vehicle based on the vehicle images included in the second image.

3. The method for planning a vehicle driving route according to claim 2, wherein, The determining the vehicle type of the at least one second vehicle includes: Determining the vehicle images corresponding to the at least one second vehicle from the second image; Determining the vehicle features of the at least one second vehicle based on the vehicle images corresponding to the at least one second vehicle; Determining the vehicle type of the at least one second vehicle based on the vehicle features of the at least one second vehicle.

4. The method for planning a vehicle driving route according to claim 2, wherein, The determining a first duration during which the at least one second vehicle appears within the preset range includes: Determining the vehicle images corresponding to the at least one second vehicle from the second image; Determining the number of consecutive frames of the vehicle images corresponding to the at least one second vehicle; Determining the first duration during which the at least one second vehicle appears within the preset range based on the number of frames of the vehicle images corresponding to the at least one second vehicle and the time interval between two adjacent frames of the vehicle images corresponding to the at least one second vehicle.

5. The method for planning a vehicle driving route according to any one of claims 1-4, wherein, The generating an avoidance instruction based on the vehicle type and the first duration includes: Determining the matching relationship between the vehicle type and a preset type; Determining the magnitude relationship between the first duration and a duration threshold; Generating the avoidance instruction based on the matching relationship between the vehicle type and the preset type and the magnitude relationship between the first duration and the duration threshold; wherein, if the vehicle type matches the preset type and the first duration is greater than or equal to the duration threshold, the avoidance instruction is generated; if the vehicle type does not match the preset type, and / or the first duration is less than the duration threshold, the avoidance instruction is not generated.

6. The method for planning a vehicle driving route according to claim 5, wherein, Before determining the matching relationship between the vehicle type and the preset type, it further includes: Collecting a first voice of a user; Determining a first type specified by the user and the time limit information of the first type based on the first voice; Generating a setting instruction based on the first type and the time limit information of the first type; Setting the preset type based on the setting instruction.

7. The method for planning a vehicle driving route according to claim 6, wherein, The determining the matching relationship between the vehicle type and the preset type includes: Determining a target type in the preset type that is valid in state during the process of planning the driving route of the vehicle; Determining the matching priority of the target type; Based on the matching priority, determine the matching relationship between the vehicle type and the target type.

8. The method for planning a vehicle driving route according to any one of claims 1-4, wherein, Planning the driving path of the first vehicle based on the avoidance instruction includes: If there are at least two second vehicles to be avoided, based on the avoidance instruction, determine the avoidance priority corresponding to each second vehicle to be avoided; Based on the avoidance priority corresponding to each second vehicle to be avoided, plan the driving path of the first vehicle.

9. An apparatus for planning a vehicle driving path, comprising: A sensing module for determining at least one second vehicle within a preset range from the first vehicle; An identification module for determining the vehicle type of the at least one second vehicle; The identification module is further configured to determine the first duration for which the at least one second vehicle appears within the preset range; A decision module for generating an avoidance instruction based on the vehicle type and the first duration; A planning module for planning the driving path of the first vehicle based on the avoidance instruction.

10. A computer-readable storage medium storing a computer program for executing the method for planning a vehicle driving path according to any one of claims 1-8 above.

11. An electronic device, the electronic device comprising: A processor; A memory for storing executable instructions of the processor; The processor is configured to read the executable instructions from the memory and execute the executable instructions to implement the method for planning a vehicle driving path according to any one of claims 1-8 above.

Images