Vehicle following target determination method and related device

Abstract

The invention discloses a vehicle following target determination method and a related device, and the method comprises the steps: obtaining related information corresponding to a plurality of candidate vehicles from a plurality of lanes, and determining the influence degree of each candidate vehicle corresponding to a vehicle according to the related information corresponding to the plurality of candidate vehicles. Wherein the influence degree is used for representing the probability that the candidate vehicles and the vehicle are located on the same lane within the first preset time, the influence of the candidate vehicles on the vehicle in the driving process can be reflected, and therefore the vehicle following target of the vehicle can be determined from the multiple candidate vehicles according to the influence degree. Therefore, the candidate vehicles in the plurality of lanes are identified in advance, and the vehicle following target is determined from the plurality of candidate vehicles according to the influence degree of each candidate vehicle on the vehicle. Therefore, the problems of untimely vehicle-following target switching, poor recognition effect or misrecognition and the like caused by only recognizing the vehicle in the lane are avoided, and the safety and comfort of automatic driving are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle control, and in particular to a method for determining a vehicle-following target and a related device. Background Art

[0002] With the continuous development of autonomous driving technology, the scenarios that need to be faced are becoming more and more numerous and complex. Among them, the following target is which vehicle in front of the vehicle is the vehicle to follow. The determination of the following target is one of the most important environmental information of the intelligent driving system. The stability, rationality and effectiveness of its selection algorithm directly affect the safety and comfort of the intelligent driving system, and are related to the user's trust and acceptance of the product.

[0003] In the related technology, a road model is generally established based on the lane line information determined by the visual algorithm, and then the target is selected as the following target through the road model. However, this method may cause the following target to switch untimely, resulting in poor safety and comfort of autonomous driving. Summary of the invention

[0004] In response to the above problems, the present application provides a method for determining a following vehicle target and related devices to improve the safety and comfort of autonomous driving.

[0005] Based on this, the embodiments of the present application disclose the following technical solutions:

[0006] On the one hand, an embodiment of the present application provides a method for determining a following vehicle target, the method comprising:

[0007] Obtaining relevant information corresponding to a plurality of candidate vehicles respectively, wherein the relevant information is information related to the corresponding vehicles, and the plurality of candidate vehicles are from a plurality of lanes;

[0008] Determine, based on the relevant information corresponding to the plurality of candidate vehicles, the degree of influence of each candidate vehicle on the vehicle, wherein the degree of influence is used to represent the probability that the candidate vehicle and the vehicle are in the same lane within a first preset time;

[0009] According to the influence degree, a following target of the host vehicle is determined from the multiple candidate vehicles.

[0010] Optionally, if the relevant information includes lane line information of the lane where the host vehicle is located, a first lateral distance, a first longitudinal distance and a width of the target candidate vehicle, the first lateral distance is the lateral distance between the host vehicle and the target candidate vehicle in the host vehicle coordinate system, the first longitudinal distance is the longitudinal distance between the host vehicle and the target candidate vehicle in the host vehicle coordinate system, the target candidate vehicle is one of the multiple candidate vehicles, and the host vehicle coordinate system is a plane rectangular coordinate system with the host vehicle as the origin, the traveling direction of the host vehicle as the first type of coordinate axis, and the direction perpendicular to the traveling direction of the host vehicle as the second type of coordinate axis;

[0011] Determining the influence degree of each candidate vehicle on the vehicle according to the relevant information corresponding to the plurality of candidate vehicles respectively includes:

[0012] Determine a second lateral distance according to the first longitudinal distance and the lane line information, where the second lateral distance is a lateral distance between the lane between the host vehicle and the target candidate vehicle and the host vehicle in the host vehicle coordinate system;

[0013] Determine a third lateral distance according to the first lateral distance, the second lateral distance and the width of the target candidate vehicle, wherein the third lateral distance is a lateral distance between the lane between the host vehicle and the target candidate vehicle and the target candidate vehicle in the host vehicle coordinate system;

[0014] Acquire a plurality of the third lateral distances within a second preset time;

[0015] If the number of the plurality of third lateral distances less than the target distance threshold is less than the first numerical threshold, determining the degree of influence of the target candidate vehicle on the host vehicle to be a first numerical value;

[0016] If the number of times that the multiple third lateral distances are less than the target distance threshold is greater than or equal to a second number threshold, the degree of influence of the target candidate vehicle on the vehicle is determined to be a second value, the second number threshold is greater than or equal to the first number threshold, and the second value is less than the first value.

[0017] Optionally, if the relevant information includes lane line information of the lane where the host vehicle is located, a first lateral distance and a first longitudinal distance, the first lateral distance is the lateral distance between the host vehicle and the target candidate vehicle in the host vehicle coordinate system, the first longitudinal distance is the longitudinal distance between the host vehicle and the target candidate vehicle in the host vehicle coordinate system, the target candidate vehicle is one of the multiple candidate vehicles, and the host vehicle coordinate system is a plane rectangular coordinate system with the host vehicle as the origin, the traveling direction of the host vehicle as the first type of coordinate axis, and the direction perpendicular to the traveling direction of the host vehicle as the second type of coordinate axis;

[0018] Determining the influence degree of each candidate vehicle on the vehicle according to the relevant information corresponding to the plurality of candidate vehicles respectively includes:

[0019] Determine a second lateral distance according to the first longitudinal distance and the lane line information, where the second lateral distance is a lateral distance between the lane between the host vehicle and the target candidate vehicle and the host vehicle in the host vehicle coordinate system;

[0020] Obtaining a corresponding relationship between the lateral distance and the degree of influence; wherein, in the corresponding relationship, the lateral distance and the degree of influence are negatively correlated;

[0021] A value of the degree of influence of the target candidate vehicle on the host vehicle is determined according to the corresponding relationship and the second lateral distance.

[0022] Optionally, if the relevant information includes a turn signal of a target candidate vehicle, the target candidate vehicle is one of the multiple candidate vehicles;

[0023] Determining the influence degree of each candidate vehicle on the vehicle according to the relevant information corresponding to the plurality of candidate vehicles respectively includes:

[0024] If the turn signal indicates that the target candidate vehicle is merging into the lane where the host vehicle is located, determining the degree of influence of the target candidate vehicle on the host vehicle as a third value;

[0025] If the turn signal indicates that the target candidate vehicle does not merge into the lane where the host vehicle is located, it is determined that the influence degree of the target candidate vehicle on the host vehicle is a fourth value, and the fourth value is less than the third value.

[0026] Optionally, if the turn signal indicates that the target candidate vehicle is merging into the lane where the host vehicle is located, determining that the degree of influence of the target candidate vehicle on the host vehicle is a third value includes:

[0027] If the time indicated by the turn signal signal that the target candidate vehicle merges into the lane where the host vehicle is located is less than the first time threshold, determining the degree of influence of the target candidate vehicle on the host vehicle as a third value;

[0028] If the turn signal signal indicates that the time for the target candidate vehicle to merge into the lane where the host vehicle is located is greater than or equal to a second time threshold, the degree of influence of the target candidate vehicle on the host vehicle is determined to be a fifth value, the second time threshold is greater than or equal to the first time threshold, and the fifth value is less than the third value.

[0029] Optionally, if the relevant information includes a lane change instruction of the vehicle;

[0030] Determining the influence degree of each candidate vehicle on the vehicle according to the relevant information corresponding to the plurality of candidate vehicles respectively includes:

[0031] If the lane that the lane change instruction indicates the host vehicle is merging into is consistent with the lane where the target candidate vehicle is located, determining that the degree of influence of the target candidate vehicle on the host vehicle is a sixth value, and the target candidate vehicle is one of the multiple candidate vehicles;

[0032] If the lane that the lane change instruction indicates the host vehicle is merging into is inconsistent with the lane where the target candidate vehicle is located, it is determined that the degree of influence of the target candidate vehicle on the host vehicle is a seventh value, and the seventh value is less than the sixth value.

[0033] Optionally, determining the following target of the vehicle from the multiple candidate vehicles according to the influence degree includes:

[0034] For a target candidate vehicle, obtaining a plurality of influence degrees, wherein the target candidate vehicle is one of the plurality of candidate vehicles;

[0035] Determining a comprehensive impact degree for the target candidate vehicle according to the multiple impact degrees;

[0036] Taking the multiple candidate vehicles as the target candidate vehicles respectively, and obtaining the comprehensive influence degree for each of the candidate vehicles;

[0037] The candidate vehicles whose comprehensive influence degree meets the preset conditions are determined as the following targets of the host vehicle.

[0038] Optionally, determining the candidate vehicle whose comprehensive influence degree meets a preset condition as the following target of the host vehicle includes:

[0039] If the candidate vehicles whose comprehensive influence degree is greater than the preset influence degree threshold include multiple ones, then the first longitudinal distance of the candidate vehicle to be determined, the longitudinal speed of the candidate vehicle to be determined, the speed of the own vehicle and the expected following distance of the own vehicle are obtained, the first longitudinal distance is the longitudinal distance between the own vehicle and the target candidate vehicle in the own vehicle coordinate system, the own vehicle coordinate system is a plane rectangular coordinate system with the own vehicle as the origin, the traveling direction of the own vehicle as the first type of coordinate axis, and the direction perpendicular to the traveling direction of the own vehicle as the second type of coordinate axis, and the candidate vehicle to be determined is the candidate vehicle whose comprehensive influence degree is greater than the preset influence degree threshold;

[0040] determining a degree of danger of the candidate vehicle to be determined according to the first longitudinal distance, the longitudinal speed, the vehicle speed, and the expected following distance;

[0041] The candidate vehicle with the highest degree of danger is determined as the following target of the host vehicle.

[0042] On the other hand, the present application provides a device for determining a vehicle-following target, the device comprising: an acquisition unit and a determination unit;

[0043] The acquisition unit is used to acquire relevant information corresponding to a plurality of candidate vehicles respectively, wherein the relevant information is information related to the corresponding vehicles, and the plurality of candidate vehicles are from a plurality of lanes;

[0044] The determination unit is used to determine the influence degree of each candidate vehicle on the host vehicle according to the relevant information corresponding to the multiple candidate vehicles, and the influence degree is used to represent the probability that the candidate vehicle and the host vehicle are in the same lane within a first preset time;

[0045] The determination unit is further configured to determine a following target of the vehicle from among the plurality of candidate vehicles according to the degree of influence.

[0046] Optionally, if the relevant information includes lane line information of the lane where the host vehicle is located, a first lateral distance, a first longitudinal distance and a width of the target candidate vehicle, the first lateral distance is the lateral distance between the host vehicle and the target candidate vehicle in the host vehicle coordinate system, the first longitudinal distance is the longitudinal distance between the host vehicle and the target candidate vehicle in the host vehicle coordinate system, the target candidate vehicle is one of the multiple candidate vehicles, and the host vehicle coordinate system is a plane rectangular coordinate system with the host vehicle as the origin, the traveling direction of the host vehicle as the first type of coordinate axis, and the direction perpendicular to the traveling direction of the host vehicle as the second type of coordinate axis;

[0047] The determining unit is specifically configured to:

[0048] Determine a second lateral distance according to the first longitudinal distance and the lane line information, where the second lateral distance is a lateral distance between the lane between the host vehicle and the target candidate vehicle and the host vehicle in the host vehicle coordinate system;

[0049] Determine a third lateral distance according to the first lateral distance, the second lateral distance and the width of the target candidate vehicle, wherein the third lateral distance is a lateral distance between the lane between the host vehicle and the target candidate vehicle and the target candidate vehicle in the host vehicle coordinate system;

[0050] Acquire a plurality of the third lateral distances within a second preset time;

[0051] If the number of the plurality of third lateral distances less than the target distance threshold is less than the first numerical threshold, determining the degree of influence of the target candidate vehicle on the host vehicle to be a first numerical value;

[0052] If the number of times that the multiple third lateral distances are less than the target distance threshold is greater than or equal to a second number threshold, the degree of influence of the target candidate vehicle on the vehicle is determined to be a second value, the second number threshold is greater than or equal to the first number threshold, and the second value is less than the first value.

[0053] Optionally, if the relevant information includes lane line information of the lane where the host vehicle is located, a first lateral distance and a first longitudinal distance, the first lateral distance is the lateral distance between the host vehicle and the target candidate vehicle in the host vehicle coordinate system, the first longitudinal distance is the longitudinal distance between the host vehicle and the target candidate vehicle in the host vehicle coordinate system, the target candidate vehicle is one of the multiple candidate vehicles, and the host vehicle coordinate system is a plane rectangular coordinate system with the host vehicle as the origin, the traveling direction of the host vehicle as the first type of coordinate axis, and the direction perpendicular to the traveling direction of the host vehicle as the second type of coordinate axis;

[0054] The determining unit is specifically configured to:

[0055] Determine a second lateral distance according to the first longitudinal distance and the lane line information, where the second lateral distance is a lateral distance between the lane between the host vehicle and the target candidate vehicle and the host vehicle in the host vehicle coordinate system;

[0056] Obtaining a corresponding relationship between the lateral distance and the degree of influence; wherein, in the corresponding relationship, the lateral distance and the degree of influence are negatively correlated;

[0057] A value of the degree of influence of the target candidate vehicle on the host vehicle is determined according to the corresponding relationship and the second lateral distance.

[0058] Optionally, if the relevant information includes a turn signal of a target candidate vehicle, the target candidate vehicle is one of the multiple candidate vehicles;

[0059] The determining unit is specifically configured to:

[0060] If the turn signal indicates that the target candidate vehicle is merging into the lane where the host vehicle is located, determining the degree of influence of the target candidate vehicle on the host vehicle as a third value;

[0061] If the turn signal indicates that the target candidate vehicle does not merge into the lane where the host vehicle is located, it is determined that the influence degree of the target candidate vehicle on the host vehicle is a fourth value, and the fourth value is less than the third value.

[0062] Optionally, the determining unit is specifically configured to:

[0063] If the time indicated by the turn signal signal that the target candidate vehicle merges into the lane where the host vehicle is located is less than the first time threshold, determining the degree of influence of the target candidate vehicle on the host vehicle as a third value;

[0064] If the turn signal signal indicates that the time for the target candidate vehicle to merge into the lane where the host vehicle is located is greater than or equal to a second time threshold, the degree of influence of the target candidate vehicle on the host vehicle is determined to be a fifth value, the second time threshold is greater than or equal to the first time threshold, and the fifth value is less than the third value.

[0065] Optionally, if the relevant information includes a lane change instruction of the vehicle;

[0066] The determining unit is specifically configured to:

[0067] If the lane that the lane change instruction indicates the host vehicle is merging into is consistent with the lane where the target candidate vehicle is located, determining that the degree of influence of the target candidate vehicle on the host vehicle is a sixth value, and the target candidate vehicle is one of the multiple candidate vehicles;

[0068] If the lane that the lane change instruction indicates the host vehicle is merging into is inconsistent with the lane where the target candidate vehicle is located, it is determined that the degree of influence of the target candidate vehicle on the host vehicle is a seventh value, and the seventh value is less than the sixth value.

[0069] Optionally, the determining unit is specifically configured to:

[0070] For a target candidate vehicle, obtaining a plurality of influence degrees, wherein the target candidate vehicle is one of the plurality of candidate vehicles;

[0071] Determining a comprehensive impact degree for the target candidate vehicle according to the multiple impact degrees;

[0072] Taking the multiple candidate vehicles as the target candidate vehicles respectively, and obtaining the comprehensive influence degree for each of the candidate vehicles;

[0073] The candidate vehicles whose comprehensive influence degree meets the preset conditions are determined as the following targets of the host vehicle.

[0074] Optionally, the determining unit is specifically configured to:

[0075] If the candidate vehicles whose comprehensive influence degree is greater than the preset influence degree threshold include multiple ones, then the first longitudinal distance of the candidate vehicle to be determined, the longitudinal speed of the candidate vehicle to be determined, the speed of the own vehicle and the expected following distance of the own vehicle are obtained, the first longitudinal distance is the longitudinal distance between the own vehicle and the target candidate vehicle in the own vehicle coordinate system, the own vehicle coordinate system is a plane rectangular coordinate system with the own vehicle as the origin, the traveling direction of the own vehicle as the first type of coordinate axis, and the direction perpendicular to the traveling direction of the own vehicle as the second type of coordinate axis, and the candidate vehicle to be determined is the candidate vehicle whose comprehensive influence degree is greater than the preset influence degree threshold;

[0076] determining a degree of danger of the candidate vehicle to be determined according to the first longitudinal distance, the longitudinal speed, the vehicle speed, and the expected following distance;

[0077] The candidate vehicle with the highest degree of danger is determined as the following target of the host vehicle.

[0078] In another aspect, the present application provides a computer device, the device comprising a processor and a memory:

[0079] The memory is used to store program code and transmit the program code to the processor;

[0080] The processor is used to execute the method described in the above aspects according to the instructions in the program code.

[0081] On the other hand, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium is used to store a computer program, and the computer program is used to execute the method described in the above aspects.

[0082] On the other hand, an embodiment of the present application provides a computer program product or a computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the method described in the above aspects.

[0083] The advantages of the above technical solution of this application are:

[0084] Obtain relevant information corresponding to multiple candidate vehicles from multiple lanes, and determine the degree of influence of each candidate vehicle on the vehicle based on the relevant information corresponding to the multiple candidate vehicles. The degree of influence is used to characterize the probability that the candidate vehicle and the vehicle are in the same lane within the first preset time, which can reflect that the vehicle will be affected by the candidate vehicle during driving, so as to determine the vehicle-to-be-followed target from multiple candidate vehicles based on the degree of influence. Thus, the candidate vehicles in multiple lanes are identified in advance, and the vehicle-to-be-followed target is determined from multiple candidate vehicles based on the degree of influence of each candidate vehicle on the vehicle. This avoids problems such as untimely switching of the vehicle-to-be-followed target, poor recognition effect, or misrecognition caused by only identifying the vehicle in the lane, thereby improving the safety and comfort of autonomous driving. BRIEF DESCRIPTION OF THE DRAWINGS

[0085] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0086] Figure 1 A flow chart of a method for determining a vehicle following target provided in this application;

[0087] Figure 2 A schematic diagram of the vehicle driving provided in this application;

[0088] Figure 3 A schematic diagram of a device for determining a vehicle-following target provided in the present application;

[0089] Figure 4 A structural diagram of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0090] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0091] In the related art, a road model is generally established based on the information of the lane line determined by the visual algorithm, and then the target in the current lane is screened out as the target to follow the vehicle through the road model. However, if only the vehicles in the current lane are compared, there may be a problem of untimely switching of the target to follow the vehicle. In addition, in the related art, although vehicles from adjacent lanes can be identified, there are problems with the timing of identification, and the target to follow is determined only based on the motion state of the cutting-in vehicle, which leads to many problems such as poor recognition effect or misidentification, resulting in poor safety and comfort of autonomous driving and poor user experience.

[0092] Based on this, the embodiment of the present application provides a method and related device for determining a following target, which obtains relevant information corresponding to multiple candidate vehicles from multiple lanes, and determines the degree of influence of each candidate vehicle on the vehicle according to the relevant information corresponding to the multiple candidate vehicles. Among them, the degree of influence is used to characterize the probability that the candidate vehicle and the vehicle are in the same lane within the first preset time, which can reflect that the vehicle will be affected by the candidate vehicle during driving, so as to determine the following target of the vehicle from multiple candidate vehicles according to the degree of influence. Thus, the candidate vehicles in multiple lanes are identified in advance, and the following target is determined from multiple candidate vehicles according to the degree of influence of each candidate vehicle on the vehicle. Thereby, problems such as untimely switching of the following target, poor recognition effect or misrecognition caused by only identifying the vehicle in the lane are avoided, and the safety and comfort of automatic driving are improved.

[0093] Combine the following Figure 1 , a method for determining a vehicle following target provided by an embodiment of the present application is introduced. Figure 1 , this figure is a flow chart of a method for determining a following vehicle target provided in an embodiment of the present application, and the method may include S101-S103.

[0094] S101: Obtain relevant information corresponding to a plurality of candidate vehicles.

[0095] The multiple candidate vehicles come from multiple lanes, for example, the multiple candidate vehicles may be five vehicles directly in front of the vehicle, in front of the left, in front of the left front, in front of the right, and in front of the right front in the driving direction of the vehicle. The relevant information is information related to the corresponding vehicle, and the relevant information of the candidate vehicle is information related to the candidate lane, for example, the relative position of the candidate vehicle and the vehicle, the first lateral distance, the second lateral distance, the third lateral distance, and the first longitudinal distance.

[0096] See also Figure 2, this figure is a schematic diagram of the driving of a vehicle provided by an embodiment of the present application. A self-vehicle coordinate system (a plane rectangular coordinate system) is established based on the vehicle, the origin of the self-vehicle coordinate system is the center of the vehicle, and the self-vehicle coordinate system includes a first type of coordinate axis and a second type of coordinate axis, the first type of coordinate axis and the second type of coordinate axis are perpendicular, and can be expressed as an x-axis and a y-axis, and the direction of the x-axis can be the direction of travel of the vehicle. Take one of the multiple candidate vehicles, that is, the target candidate vehicle, as an example for explanation. The first lateral distance is the lateral distance between the vehicle and the target candidate vehicle in the self-vehicle coordinate system, and the first longitudinal distance is the longitudinal distance between the vehicle and the target candidate vehicle in the self-vehicle coordinate system. For example, the relevant information of the candidate vehicle can be obtained through a camera and various sensors.

[0097] As a possible implementation method, for each candidate vehicle at a position, if there is no vehicle at that position, the relevant information of the candidate vehicle cannot be obtained. In this case, the first longitudinal distance can be set to 100 meters, the first lateral distance to 3 meters, the longitudinal speed to the vehicle speed, the vehicle width to 1.8 meters, and the turn signal to false to facilitate subsequent calculations and processing.

[0098] S102: Determine the influence degree of each candidate vehicle on the vehicle according to the relevant information corresponding to each of the plurality of candidate vehicles.

[0099] The degree of influence is used to characterize the probability that the candidate vehicle is in the same lane as the vehicle within the first preset time, or in other words, the probability that the candidate vehicle is about to be in the same lane as the vehicle, such as the candidate vehicle changes lanes and cuts into the lane where the vehicle is located, thereby affecting the driving of the vehicle.

[0100] As a possible implementation, the influence degree includes the driving stability of each candidate vehicle, the distance between each candidate vehicle and the vehicle, the lane change intention of each candidate vehicle, and multiple combinations of the lane change intention of the vehicle. Each of these is described below.

[0101] Method 1: The relevant information includes the lane line information of the lane where the vehicle is located, the first lateral distance, the first longitudinal distance and the width of the target candidate vehicle. The driving stability of each candidate vehicle, that is, the degree of influence of each candidate vehicle on the vehicle, can be determined in the following way.

[0102] A1: Determine the second lateral distance according to the first longitudinal distance and lane line information.

[0103] The second lateral distance is the lateral distance between the lane between the vehicle and the target candidate vehicle and the vehicle in the vehicle coordinate system.

[0104] Continue to see Figure 2 , the lane line between the vehicle and the target candidate vehicle can be expressed as y = a0 + a1x + a2x2 +a3x 3 , where y represents the lane line, x represents the first longitudinal distance, and a0, a1, a2, and a3 are the parameters of the fitting curve, which can be obtained through calibration. The second lateral distance can be expressed as Among them, d LaneLat Expressed as the second lateral distance, d VehLon Expressed as the first longitudinal distance.

[0105] A2: Determine a third lateral distance according to the first lateral distance, the second lateral distance, and the width of the candidate target vehicle.

[0106] The third lateral distance is the lateral distance between the lane between the vehicle and the target candidate vehicle and the target candidate vehicle in the vehicle coordinate system. Figure 2 , the third lateral distance can be expressed as Among them, d VehToLaneLat represents the third lateral distance, d VehLat represents the first lateral distance, d LaneLat Expressed as the second lateral distance, d Widt h represents the width of the target candidate vehicle.

[0107] A3: Acquire multiple third horizontal distances within the second preset time.

[0108] According to the third lateral distance from the lane line in the target candidate vehicle, the motion state of the target candidate vehicle is determined. If the distance from the lane line (i.e., the lane line between the target candidate vehicle and the host vehicle) is less than the target distance threshold more times within the second preset time, it means that the target candidate vehicle is constantly approaching the lane line and may cut into the host lane, which is likely to affect the driving of the host vehicle. If the distance from the lane line of the target candidate vehicle is less than the target distance threshold less times, it means that the target candidate vehicle is less likely to affect the driving of the host vehicle. Based on this, the degree of influence of the target candidate vehicle on the host vehicle can be determined.

[0109] A4: If the number of the plurality of third lateral distances that are less than the target distance threshold is less than the first numerical threshold, then the influence degree of the target candidate vehicle on the host vehicle is determined to be a first numerical value.

[0110] A5: If the number of times that the plurality of third lateral distances are less than the target distance threshold is greater than or equal to the second numerical threshold, it is determined that the degree of influence of the target candidate vehicle on the vehicle is a second numerical value.

[0111] The second numerical threshold is greater than or equal to the first numerical threshold, and the second value is less than the first value. The degree of influence can be expressed as follows:

[0112]

[0113] Among them, Confidence1 represents the influence degree of the target candidate vehicle on the vehicle, Gx1 represents the first value, Gx2 represents the second value, C1 represents the first numerical threshold, and C2 represents the second numerical threshold.

[0114] Method 2: If the relevant information includes the lane line information of the lane where the vehicle is located, the first lateral distance and the first longitudinal distance, the distance between each candidate vehicle and the vehicle, that is, the degree of influence of each candidate vehicle on the vehicle, can be determined in the following manner.

[0115] B1: Determine the second lateral distance based on the first longitudinal distance and lane line information.

[0116] The second lateral distance is the lateral distance between the lane between the host vehicle and the target candidate vehicle and the host vehicle in the host vehicle coordinate system. The second lateral distance may be determined in the manner described in A1 above.

[0117] B2: Obtain the corresponding relationship between the lateral distance and the impact degree.

[0118] Among them, in the correspondence relationship between the lateral distance and the influence degree, the lateral distance and the influence degree are negatively correlated. The correspondence relationship can be calibrated in advance.

[0119] B3: Determine the value of the influence degree of the target candidate vehicle on the vehicle according to the corresponding relationship and the second lateral distance.

[0120] According to the corresponding relationship, the influence degree corresponding to the second lateral distance is determined and used as the value of the influence degree of the target candidate vehicle on the vehicle, which is equivalent to the process of looking up a table and can be expressed as the following formula:

[0121] d VehToLaneLat →f(d VehToLaneLat )→Confidence2

[0122] Among them, d VehToLaneLat represents the second lateral distance, f(d VehToLaneLat ) represents the corresponding relationship between the lateral distance and the degree of influence, and Confidence2 represents the numerical value of the degree of influence of the target candidate vehicle on the vehicle.

[0123] Method three, the relevant information includes the turn signal of the target candidate vehicle, and the lane change intention of each candidate vehicle can be determined in the following way, that is, the degree of influence of each candidate vehicle on the vehicle.

[0124] C1: If the turn signal indicates that the target candidate vehicle is merging into the lane where the host vehicle is located, then the degree of influence of the target candidate vehicle on the host vehicle is determined to be a third value.

[0125] C2: If the turn signal indicates that the target candidate vehicle will not merge into the lane where the host vehicle is located, then the influence degree of the target candidate vehicle on the host vehicle is determined to be a fourth value.

[0126] Among them, the fourth value is less than the third value. As a possible implementation method, the turn signal of the target candidate vehicle turning left or right can be obtained according to the front camera of the vehicle. As a possible implementation method, short-term false true signals can be filtered out to reduce false triggering. Multiple valid true signals are connected to improve the consistency of the behavior of the adjacent vehicle and avoid frequent jumps in the impact degree of the final output.

[0127] For example, if the target candidate vehicle is located in front of the left side of the vehicle, if the turn signal is to turn right, that is, to indicate that the target candidate vehicle is merging into the lane where the vehicle is located, then it is determined that the target candidate vehicle has a high degree of influence on the vehicle. If the turn signal is to turn left, that is, to indicate that the target candidate vehicle is merging into a lane other than the vehicle is located, then it is determined that the target candidate vehicle has a low degree of influence on the vehicle. It can be expressed as follows:

[0128]

[0129] Among them, Confidence 3RAW Indicates the degree of influence of the target candidate vehicle on the vehicle.

[0130] As a possible implementation method, since there are larger vehicles such as trucks in actual working conditions, when collecting signal lights, the large double flashes of larger vehicles may be mistaken for turn signals, and vehicles may turn for a long time but do not merge into the lane where the vehicle is located. In this case, the true turn signal signal pointing to the lane can be processed, and its impact can be gradually reduced over time to improve recognition accuracy.

[0131] Specifically, if the turn signal signal indicates that the time for the target candidate vehicle to merge into the lane where the vehicle is located is less than the first time threshold, the degree of influence of the target candidate vehicle on the vehicle is determined to be a third value; if the turn signal signal indicates that the time for the target candidate vehicle to merge into the lane where the vehicle is located is greater than or equal to the second time threshold, the degree of influence of the target candidate vehicle on the vehicle is determined to be a fifth value.

[0132] The second time threshold is greater than or equal to the first time threshold, and the fifth value is less than the third value. It can be expressed as the following formula:

[0133]

[0134] Among them, Confidence3 represents the influence degree of the target candidate vehicle on the vehicle, C3 represents the first time threshold, C4 represents the second time threshold, and Confidence 3RAWrepresents the third value, f(time) represents the proportional coefficient obtained according to the time mapping, which can be any value between 0 and 1, Confidence 3RAW ×f(time) represents the fifth numerical value.

[0135] Method 4: If the relevant information includes the lane change instruction of the vehicle, the lane change intention of the vehicle can be determined in the following way.

[0136] D1: If the lane that the lane change instruction indicates the host vehicle to merge into is consistent with the lane where the target candidate vehicle is located, then the degree of influence of the target candidate vehicle on the host vehicle is determined to be a sixth value.

[0137] D2: If the lane that the lane change instruction indicates the host vehicle to merge into is inconsistent with the lane where the target candidate vehicle is located, then the degree of influence of the target candidate vehicle on the host vehicle is determined to be the seventh value.

[0138] The seventh value is less than the sixth value. Lane change instructions include but are not limited to on-ramp and off-ramp, defensive driving for cutting-in vehicles, etc. The greater the possibility that the vehicle merges into the lane where the target candidate vehicle is located, the higher the degree of influence, which can be expressed as the following formula:

[0139]

[0140] Among them, Confidence4 represents the influence degree of the target candidate vehicle on the vehicle.

[0141] It should be noted that relevant information about the vehicle body posture can be obtained through sensor and software output information; lane line information can be obtained through the vehicle's front-view camera; and the vehicle's motion state and lane change intention can be obtained based on the vehicle's relevant information.

[0142] S103: Determine a following target of the vehicle from among multiple candidate vehicles according to the degree of influence.

[0143] As a possible implementation method, the following vehicle target of the vehicle can be determined from multiple candidate vehicles based on multiple combinations of the influence degrees determined by the above four methods. The following methods can be used:

[0144] E1: Obtain multiple impact levels for target candidate vehicles.

[0145] E2: Determine the comprehensive impact degree for the target candidate vehicle based on multiple impact degrees.

[0146] Taking multiple influence degrees as an example to obtain the influence degree of each candidate vehicle in the dimension of driving stability, the influence degree of each candidate vehicle in the dimension of distance between the candidate vehicle and the vehicle, the influence degree of each candidate vehicle in the dimension of lane change intention, and the influence degree of the vehicle in the dimension of lane change intention, the comprehensive influence degree can be expressed as follows:

[0147] Confidence

[0148] =k1×Confidence1+k2×Confidence2+k3×Confidence3

[0149] +k4×Confidence4

[0150] Among them, Confidence is expressed as the comprehensive influence degree, Confidence1 represents the influence degree of the target candidate vehicle on the vehicle in the dimension of driving stability, Confidence2 represents the influence degree of the distance dimension between the target candidate vehicle and the vehicle, Confidence3 represents the influence degree of the target candidate vehicle in the dimension of lane change intention, Confidence4 represents the influence degree of the target candidate vehicle in the dimension of lane change intention of the vehicle, and k1-k4 are the corresponding weights.

[0151] E3: Take multiple candidate vehicles as target candidate vehicles respectively, and obtain the comprehensive impact degree of each candidate vehicle.

[0152] E4: Determine the candidate vehicles whose comprehensive impact degree meets the preset conditions as the following targets of this vehicle.

[0153] For example, the candidate vehicle with the greatest comprehensive influence is determined as the following target of this vehicle.

[0154] As a possible implementation method, if there are multiple candidate vehicles whose comprehensive influence degree is greater than a preset influence degree threshold, the first longitudinal distance of the candidate vehicle to be determined, the longitudinal speed of the candidate vehicle to be determined, the speed of the vehicle and the expected following distance of the vehicle to be determined are obtained; the danger degree of the candidate vehicle to be determined is determined according to the first longitudinal distance, the longitudinal speed, the speed and the expected following distance; the candidate vehicle to be determined with the highest danger degree is determined as the following target of the vehicle, which can be expressed as the following formula:

[0155] DangerousValue=k5×(d VehLon -d dsrd )+k6×(v VehLon -v ego )

[0156] DangerousValue represents the degree of danger of the candidate vehicle to be determined, d VehLon It is represented as the first longitudinal distance of the candidate vehicle to be determined, d dsrd It is expressed as the expected following distance of the vehicle, v VehLon Denotes the longitudinal velocity of the candidate vehicle, v ego It is represented as the speed of the vehicle, and k5 and k6 are the corresponding weights.

[0157] Therefore, the following target is selected in advance by considering the vehicle's own behavior state and the behavior state of the surrounding target vehicles, which is proactive. At the same time, the influence degree of each candidate vehicle is provided, and the following effect can be adjusted more humanely according to this influence degree, improving driving comfort and stability. In addition, by referring to the candidate vehicles in the current lane and the candidate vehicles in the adjacent lane, the following target is selected in advance and the target vehicle in the lane is released in advance, which is safe and improves the continuity of lane change action.

[0158] It can be seen from the above technical solution that the relevant information corresponding to multiple candidate vehicles from multiple lanes is obtained, and the degree of influence of each candidate vehicle on the vehicle is determined according to the relevant information corresponding to the multiple candidate vehicles. Among them, the degree of influence is used to characterize the probability that the candidate vehicle and the vehicle are in the same lane within the first preset time, which can reflect that the vehicle will be affected by the candidate vehicle during driving, so as to determine the following target of the vehicle from multiple candidate vehicles according to the degree of influence. Thus, the candidate vehicles in multiple lanes are identified in advance, and the following target is determined from multiple candidate vehicles according to the degree of influence of each candidate vehicle on the vehicle. Thereby, problems such as untimely switching of the following target, poor recognition effect or misrecognition caused by only identifying the vehicle in the lane are avoided, and the safety and comfort of automatic driving are improved.

[0159] In addition to the method for determining a vehicle following target provided in the embodiment of the present application, a device for determining a vehicle following target is also provided, such as Figure 3 As shown, it includes: an acquisition unit 301 and a determination unit 302;

[0160] The acquisition unit 301 is used to acquire relevant information corresponding to a plurality of candidate vehicles, wherein the relevant information is information related to the corresponding vehicle, and the plurality of candidate vehicles are from a plurality of lanes;

[0161] The determining unit 302 is used to determine the influence degree of each candidate vehicle on the vehicle according to the relevant information corresponding to the multiple candidate vehicles, and the influence degree is used to represent the probability that the candidate vehicle and the vehicle are in the same lane within a first preset time;

[0162] The determining unit 302 is further configured to determine a following target of the host vehicle from among the plurality of candidate vehicles according to the degree of influence.

[0163] It can be seen from the above technical solution that the relevant information corresponding to multiple candidate vehicles from multiple lanes is obtained, and the degree of influence of each candidate vehicle on the vehicle is determined according to the relevant information corresponding to the multiple candidate vehicles. Among them, the degree of influence is used to characterize the probability that the candidate vehicle and the vehicle are in the same lane within the first preset time, which can reflect that the vehicle will be affected by the candidate vehicle during driving, so as to determine the following target of the vehicle from multiple candidate vehicles according to the degree of influence. Thus, the candidate vehicles in multiple lanes are identified in advance, and the following target is determined from multiple candidate vehicles according to the degree of influence of each candidate vehicle on the vehicle. Thereby, problems such as untimely switching of the following target, poor recognition effect or misrecognition caused by only identifying the vehicle in the lane are avoided, and the safety and comfort of automatic driving are improved.

[0164] As a possible implementation manner, if the relevant information includes lane line information of the lane where the host vehicle is located, a first lateral distance, a first longitudinal distance and a width of the target candidate vehicle, the first lateral distance is the lateral distance between the host vehicle and the target candidate vehicle in the host vehicle coordinate system, the first longitudinal distance is the longitudinal distance between the host vehicle and the target candidate vehicle in the host vehicle coordinate system, the target candidate vehicle is one of the multiple candidate vehicles, and the host vehicle coordinate system is a plane rectangular coordinate system with the host vehicle as the origin, the traveling direction of the host vehicle as the first type of coordinate axis, and the direction perpendicular to the traveling direction of the host vehicle as the second type of coordinate axis;

[0165] The determining unit 302 is specifically configured to:

[0166] Determine a second lateral distance according to the first longitudinal distance and the lane line information, where the second lateral distance is a lateral distance between the lane between the host vehicle and the target candidate vehicle and the host vehicle in the host vehicle coordinate system;

[0167] Determine a third lateral distance according to the first lateral distance, the second lateral distance and the width of the target candidate vehicle, wherein the third lateral distance is a lateral distance between the lane between the host vehicle and the target candidate vehicle and the target candidate vehicle in the host vehicle coordinate system;

[0168] Acquire a plurality of the third lateral distances within a second preset time;

[0169] If the number of the plurality of third lateral distances less than the target distance threshold is less than the first numerical threshold, determining the degree of influence of the target candidate vehicle on the host vehicle to be a first numerical value;

[0170] If the number of times that the multiple third lateral distances are less than the target distance threshold is greater than or equal to a second number threshold, the degree of influence of the target candidate vehicle on the vehicle is determined to be a second value, the second number threshold is greater than or equal to the first number threshold, and the second value is less than the first value.

[0171] As a possible implementation manner, if the relevant information includes lane line information of the lane where the host vehicle is located, a first lateral distance and a first longitudinal distance, the first lateral distance is the lateral distance between the host vehicle and the target candidate vehicle in the host vehicle coordinate system, the first longitudinal distance is the longitudinal distance between the host vehicle and the target candidate vehicle in the host vehicle coordinate system, the target candidate vehicle is one of the multiple candidate vehicles, and the host vehicle coordinate system is a plane rectangular coordinate system with the host vehicle as the origin, the traveling direction of the host vehicle as the first type of coordinate axis, and the direction perpendicular to the traveling direction of the host vehicle as the second type of coordinate axis;

[0172] The determining unit 302 is specifically configured to:

[0173] Determine a second lateral distance according to the first longitudinal distance and the lane line information, where the second lateral distance is a lateral distance between the lane between the host vehicle and the target candidate vehicle and the host vehicle in the host vehicle coordinate system;

[0174] Obtaining a corresponding relationship between the lateral distance and the degree of influence; wherein, in the corresponding relationship, the lateral distance and the degree of influence are negatively correlated;

[0175] A value of the degree of influence of the target candidate vehicle on the host vehicle is determined according to the corresponding relationship and the second lateral distance.

[0176] As a possible implementation manner, if the relevant information includes a turn signal of a target candidate vehicle, the target candidate vehicle is one of the multiple candidate vehicles;

[0177] The determining unit 302 is specifically configured to:

[0178] If the turn signal indicates that the target candidate vehicle is merging into the lane where the host vehicle is located, determining the degree of influence of the target candidate vehicle on the host vehicle as a third value;

[0179] If the turn signal indicates that the target candidate vehicle does not merge into the lane where the host vehicle is located, it is determined that the influence degree of the target candidate vehicle on the host vehicle is a fourth value, and the fourth value is less than the third value.

[0180] As a possible implementation manner, the determining unit 302 is specifically configured to:

[0181] If the time indicated by the turn signal signal that the target candidate vehicle merges into the lane where the host vehicle is located is less than the first time threshold, determining the degree of influence of the target candidate vehicle on the host vehicle as a third value;

[0182] If the turn signal signal indicates that the time for the target candidate vehicle to merge into the lane where the host vehicle is located is greater than or equal to a second time threshold, the degree of influence of the target candidate vehicle on the host vehicle is determined to be a fifth value, the second time threshold is greater than or equal to the first time threshold, and the fifth value is less than the third value.

[0183] As a possible implementation manner, if the relevant information includes a lane change instruction of the vehicle;

[0184] The determining unit 302 is specifically configured to:

[0185] If the lane that the lane change instruction indicates the host vehicle is merging into is consistent with the lane where the target candidate vehicle is located, determining that the degree of influence of the target candidate vehicle on the host vehicle is a sixth value, and the target candidate vehicle is one of the multiple candidate vehicles;

[0186] If the lane that the lane change instruction indicates the host vehicle is merging into is inconsistent with the lane where the target candidate vehicle is located, it is determined that the degree of influence of the target candidate vehicle on the host vehicle is a seventh value, and the seventh value is less than the sixth value.

[0187] As a possible implementation manner, the determining unit 302 is specifically configured to:

[0188] For a target candidate vehicle, obtaining a plurality of influence degrees, wherein the target candidate vehicle is one of the plurality of candidate vehicles;

[0189] Determining a comprehensive impact degree for the target candidate vehicle according to the multiple impact degrees;

[0190] Taking the multiple candidate vehicles as the target candidate vehicles respectively, and obtaining the comprehensive influence degree for each of the candidate vehicles;

[0191] The candidate vehicles whose comprehensive influence degree meets the preset conditions are determined as the following targets of the host vehicle.

[0192] As a possible implementation manner, the determining unit 302 is specifically configured to:

[0193] If the candidate vehicles whose comprehensive influence degree is greater than the preset influence degree threshold include multiple ones, then the first longitudinal distance of the candidate vehicle to be determined, the longitudinal speed of the candidate vehicle to be determined, the speed of the own vehicle and the expected following distance of the own vehicle are obtained, the first longitudinal distance is the longitudinal distance between the own vehicle and the target candidate vehicle in the own vehicle coordinate system, the own vehicle coordinate system is a plane rectangular coordinate system with the own vehicle as the origin, the traveling direction of the own vehicle as the first type of coordinate axis, and the direction perpendicular to the traveling direction of the own vehicle as the second type of coordinate axis, and the candidate vehicle to be determined is the candidate vehicle whose comprehensive influence degree is greater than the preset influence degree threshold;

[0194] determining a degree of danger of the candidate vehicle to be determined according to the first longitudinal distance, the longitudinal speed, the vehicle speed, and the expected following distance;

[0195] The candidate vehicle with the highest degree of danger is determined as the following target of the host vehicle.

[0196] The present application also provides a computer device, see Figure 4 , which shows a structural diagram of a computer device provided in an embodiment of the present application, such as Figure 4 As shown, the device includes a memory 410 and a processor 420:

[0197] The memory 410 is used to store program codes and transmit the program codes to the processor;

[0198] The processor 420 is used to execute any of the following vehicle target determination methods provided in the above embodiments according to the instructions in the program code.

[0199] An embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium is used to store a computer program, wherein the computer program is used to execute any of the methods for determining a following vehicle target provided in the above embodiments.

[0200] The embodiment of the present application also provides a computer program product or a computer program, which includes a computer instruction stored in a computer-readable storage medium. The processor of the computer device reads the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the computer device executes the method for determining the following vehicle target provided in various optional implementations of the above aspects.

[0201] It should be noted that the various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments, and the same or similar parts between the various embodiments can be referred to each other. For the system or device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0202] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0203] It should also be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0204] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0205] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for determining a vehicle following target, characterized in that: The method comprises: Obtaining relevant information corresponding to a plurality of candidate vehicles respectively, wherein the relevant information is information related to the corresponding vehicles, and the plurality of candidate vehicles are from a plurality of lanes; Determine, based on the relevant information corresponding to the plurality of candidate vehicles, the degree of influence of each candidate vehicle on the vehicle, wherein the degree of influence is used to represent the probability that the candidate vehicle and the vehicle are in the same lane within a first preset time; According to the influence degree, a following target of the host vehicle is determined from the multiple candidate vehicles.

2. The method according to claim 1, characterized in that If the relevant information includes lane line information of the lane where the host vehicle is located, a first lateral distance, a first longitudinal distance and a width of the target candidate vehicle, the first lateral distance is the lateral distance between the host vehicle and the target candidate vehicle in the host vehicle coordinate system, the first longitudinal distance is the longitudinal distance between the host vehicle and the target candidate vehicle in the host vehicle coordinate system, the target candidate vehicle is one of the multiple candidate vehicles, and the host vehicle coordinate system is a plane rectangular coordinate system with the host vehicle as the origin, the traveling direction of the host vehicle as the first type of coordinate axis, and the direction perpendicular to the traveling direction of the host vehicle as the second type of coordinate axis; Determining the influence degree of each candidate vehicle on the vehicle according to the relevant information corresponding to the plurality of candidate vehicles respectively includes: Determine a second lateral distance according to the first longitudinal distance and the lane line information, where the second lateral distance is a lateral distance between the lane between the host vehicle and the target candidate vehicle and the host vehicle in the host vehicle coordinate system; Determine a third lateral distance according to the first lateral distance, the second lateral distance and the width of the target candidate vehicle, wherein the third lateral distance is a lateral distance between the lane between the host vehicle and the target candidate vehicle and the target candidate vehicle in the host vehicle coordinate system; Acquire a plurality of the third lateral distances within a second preset time; If the number of the plurality of third lateral distances less than the target distance threshold is less than the first numerical threshold, determining the degree of influence of the target candidate vehicle on the host vehicle to be a first numerical value; If the number of times that the multiple third lateral distances are less than the target distance threshold is greater than or equal to a second number threshold, the degree of influence of the target candidate vehicle on the vehicle is determined to be a second value, the second number threshold is greater than or equal to the first number threshold, and the second value is less than the first value.

3. The method according to claim 1, characterized in that If the relevant information includes lane line information of the lane where the host vehicle is located, a first lateral distance and a first longitudinal distance, the first lateral distance is the lateral distance between the host vehicle and the target candidate vehicle in the host vehicle coordinate system, the first longitudinal distance is the longitudinal distance between the host vehicle and the target candidate vehicle in the host vehicle coordinate system, the target candidate vehicle is one of the multiple candidate vehicles, and the host vehicle coordinate system is a plane rectangular coordinate system with the host vehicle as the origin, the traveling direction of the host vehicle as the first type of coordinate axis, and the direction perpendicular to the traveling direction of the host vehicle as the second type of coordinate axis; Determining the influence degree of each candidate vehicle on the vehicle according to the relevant information corresponding to the plurality of candidate vehicles respectively includes: Determine a second lateral distance according to the first longitudinal distance and the lane line information, where the second lateral distance is a lateral distance between the lane between the host vehicle and the target candidate vehicle and the host vehicle in the host vehicle coordinate system; Obtaining a corresponding relationship between the lateral distance and the degree of influence; wherein, in the corresponding relationship, the lateral distance and the degree of influence are negatively correlated; A value of the degree of influence of the target candidate vehicle on the host vehicle is determined according to the corresponding relationship and the second lateral distance.

4. The method according to claim 1, characterized in that: If the relevant information includes a turn signal of a target candidate vehicle, the target candidate vehicle is one of the multiple candidate vehicles; Determining the influence degree of each candidate vehicle on the vehicle according to the relevant information corresponding to the plurality of candidate vehicles respectively includes: If the turn signal indicates that the target candidate vehicle is merging into the lane where the host vehicle is located, determining the degree of influence of the target candidate vehicle on the host vehicle as a third value; If the turn signal indicates that the target candidate vehicle does not merge into the lane where the host vehicle is located, it is determined that the influence degree of the target candidate vehicle on the host vehicle is a fourth value, and the fourth value is less than the third value.

5. The method according to claim 4, characterized in that If the turn signal indicates that the target candidate vehicle is merging into the lane where the host vehicle is located, determining that the influence degree of the target candidate vehicle on the host vehicle is a third value, comprises: If the time indicated by the turn signal signal that the target candidate vehicle merges into the lane where the host vehicle is located is less than the first time threshold, determining the degree of influence of the target candidate vehicle on the host vehicle as a third value; If the turn signal signal indicates that the time for the target candidate vehicle to merge into the lane where the host vehicle is located is greater than or equal to a second time threshold, the degree of influence of the target candidate vehicle on the host vehicle is determined to be a fifth value, the second time threshold is greater than or equal to the first time threshold, and the fifth value is less than the third value.

6. The method according to claim 1, characterized in that If the relevant information includes a lane change instruction of the vehicle; Determining the influence degree of each candidate vehicle on the vehicle according to the relevant information corresponding to the plurality of candidate vehicles respectively includes: If the lane that the lane change instruction indicates the host vehicle is merging into is consistent with the lane where the target candidate vehicle is located, determining that the degree of influence of the target candidate vehicle on the host vehicle is a sixth value, and the target candidate vehicle is one of the multiple candidate vehicles; If the lane that the lane change instruction indicates the host vehicle is merging into is inconsistent with the lane where the target candidate vehicle is located, it is determined that the degree of influence of the target candidate vehicle on the host vehicle is a seventh value, and the seventh value is less than the sixth value.

7. The method according to claim 1, characterized in that The determining, according to the influence degree, a following target of the host vehicle from the plurality of candidate vehicles comprises: For a target candidate vehicle, obtaining a plurality of influence degrees, wherein the target candidate vehicle is one of the plurality of candidate vehicles; Determining a comprehensive impact degree for the target candidate vehicle according to the multiple impact degrees; Taking the multiple candidate vehicles as the target candidate vehicles respectively, and obtaining the comprehensive influence degree for each of the candidate vehicles; The candidate vehicles whose comprehensive influence degree meets the preset conditions are determined as the following targets of the host vehicle.

8. The method according to claim 7, characterized in that The step of determining the candidate vehicle whose comprehensive influence degree meets the preset condition as the following target of the host vehicle includes: If the candidate vehicles whose comprehensive influence degree is greater than the preset influence degree threshold include multiple ones, then the first longitudinal distance of the candidate vehicle to be determined, the longitudinal speed of the candidate vehicle to be determined, the speed of the own vehicle and the expected following distance of the own vehicle are obtained, the first longitudinal distance is the longitudinal distance between the own vehicle and the target candidate vehicle in the own vehicle coordinate system, the own vehicle coordinate system is a plane rectangular coordinate system with the own vehicle as the origin, the traveling direction of the own vehicle as the first type of coordinate axis, and the direction perpendicular to the traveling direction of the own vehicle as the second type of coordinate axis, and the candidate vehicle to be determined is the candidate vehicle whose comprehensive influence degree is greater than the preset influence degree threshold; determining a degree of danger of the candidate vehicle to be determined according to the first longitudinal distance, the longitudinal speed, the vehicle speed, and the expected following distance; The candidate vehicle with the highest degree of danger is determined as the following target of the host vehicle.

9. A device for determining a vehicle following target, characterized in that: The device comprises: an acquisition unit and a determination unit; The acquisition unit is used to acquire relevant information corresponding to a plurality of candidate vehicles respectively, wherein the relevant information is information related to the corresponding vehicles, and the plurality of candidate vehicles are from a plurality of lanes; The determination unit is used to determine the influence degree of each candidate vehicle on the host vehicle according to the relevant information corresponding to the multiple candidate vehicles, and the influence degree is used to represent the probability that the candidate vehicle and the host vehicle are in the same lane within a first preset time; The determination unit is further configured to determine a following target of the vehicle from among the plurality of candidate vehicles according to the degree of influence.

10. A computer device, characterized in that: The device comprises a processor and a memory: The memory is used to store program code and transmit the program code to the processor; The processor is used to execute the method according to any one of claims 1 to 8 according to the instructions in the program code.

Images