Target screening method and system based on greedy algorithm, vehicle and equipment

Abstract

The invention discloses a target screening method and system based on a greedy algorithm, a vehicle and equipment. The target screening method based on the greedy algorithm comprises the following steps: performing effective screening on obstacles in a set range around a vehicle to obtain an effective screening target; sorting the effective screening targets according to a preset sorting rule; according to the sequence, calculating a target screening coefficient of each effective screening target in sequence; if the target screening coefficient of the current effective screening target is larger than a preset threshold value, a scene comprehensive screening coefficient is obtained according to the target screening coefficient of the current effective screening target, and otherwise, the current effective screening target serves as a final screening target, and the attribute of the final screening target is output. With the adoption of the method and the device, the target obstacle can be screened more accurately and efficiently on the premise of ensuring safety, and the driving comfort is effectively improved.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and in particular to a target screening method, system, vehicle and equipment based on a greedy algorithm. Background Art

[0002] With the vigorous development of the automobile industry, intelligent driving has gradually entered people's lives. As an important part of assisted intelligent driving, adaptive cruise control (ACC) technology has received widespread attention. So far, the ACC system has been fully proven to have the function of reducing driver fatigue and improving vehicle driving safety, and has been widely used. The existing screening strategy generally screens out obstacles that are within the driving trajectory of the vehicle and the target with the closest longitudinal position to the vehicle. If the target is too close or suddenly cuts into the lane, it will cause frequent braking, which is easy to cause braking or acceleration that is inconsistent with the habits of human drivers, causing shock and distress to the driver, and to a certain extent, losing the meaning of using the comfort auxiliary driving function. For human drivers, when encountering this situation during driving, they generally control the steering wheel to make the vehicle slightly deviate from the center line of the lane to avoid the target that invades the lane. In this way, the vehicle speed is relatively stable, and driving safety and comfort can be guaranteed. Since the ACC system only controls the longitudinal direction of the vehicle, and the lateral direction of the vehicle is controlled by the driver through the steering wheel, the screening of targets needs to be optimized. Summary of the invention

[0003] Based on this, it is necessary to provide a target screening method, system, vehicle and equipment based on a greedy algorithm to address the above technical problems, which can screen target obstacles more accurately and efficiently while ensuring safety, thereby effectively improving driving comfort.

[0004] In a first aspect, a target screening method based on a greedy algorithm is provided, comprising:

[0005] Perform effectiveness screening on obstacles within a set range around the vehicle to obtain effectiveness screening targets;

[0006] Sorting the effectiveness screening targets according to predetermined sorting rules;

[0007] According to the ranking, the target screening coefficient of each effectiveness screening target is calculated in turn;

[0008] If the target screening coefficient of the current validity screening target is greater than a predetermined threshold, the scenario comprehensive screening coefficient is obtained based on the target screening coefficient of the current validity screening target; otherwise, the current validity screening target is used as the final screening target, and the attributes of the final screening target are output.

[0009] In some examples, the effectiveness screening of obstacles within a set range around the vehicle to obtain the effectiveness screening target includes:

[0010] The effectiveness of target recognition and recognition range is judged for obstacles within the set range around the vehicle to obtain effectiveness screening targets.

[0011] In some examples, the sorting of effectiveness screening targets according to a predetermined sorting rule includes:

[0012] The validity screening targets are sorted according to their longitudinal positions from near to far, wherein when the longitudinal positions of any two validity screening targets are the same, the said any two validity screening targets are sorted from left to right first.

[0013] In some examples, calculating the target screening coefficient of each effectiveness screening target in sequence according to the ranking includes:

[0014] Calculate the driving comfort index ξ for each effectiveness screening target com 、Evasion convenience indexξ avo 、Collision loss indexξ loss and collision probability index ξ pro ;

[0015] According to the driving comfort index ξ com 、Evasion convenience indexξ avo 、Collision loss indexξ loss and collision probability index ξ pro , and obtain the target screening coefficient for each effectiveness screening target.

[0016] In some examples, the driving comfort index calculation formula is:

[0017]

[0018] Among them, δ s represents the steering wheel angle of the vehicle, Δδ s represents the steering wheel speed of the vehicle; a o Represents the longitudinal acceleration of the vehicle, v o Represents the longitudinal velocity value of the vehicle;

[0019] The calculation formula of the avoidance convenience index is:

[0020]

[0021] in, represents the road curvature, a o Represents the longitudinal acceleration of the vehicle, v orepresents the longitudinal velocity of the vehicle, a e Represents the longitudinal acceleration value of the obstacle vehicle, v e Represents the longitudinal speed of the obstacle vehicle, S e Represents the longitudinal value of the obstacle vehicle in the SL coordinate system, L e Represents the lateral value of the obstacle vehicle in the SL coordinate system;

[0022] The calculation formula of collision loss index is:

[0023]

[0024] in, represents the road curvature, v o Represents the longitudinal velocity of the vehicle, v e Represents the longitudinal velocity of the obstacle vehicle, L e Represents the lateral value of the obstacle vehicle in the SL coordinate system;

[0025] The calculation formula of collision probability index is:

[0026]

[0027] in, represents the road curvature, δ s represents the steering wheel angle of the vehicle, TTC represents the collision time, L e Represents the lateral value of the obstacle vehicle in the SL coordinate system.

[0028] In some examples, after the target screening coefficient of the current validity screening target is greater than a predetermined threshold and the scenario comprehensive screening coefficient is obtained according to the target screening coefficient of the current validity screening target, the method further includes:

[0029] Determining whether the scene comprehensive screening coefficient is greater than the predetermined threshold;

[0030] If not, the current validity screening target is used as the final screening target, and the attributes of the final screening target are output.

[0031] In some examples, the attributes of the final screening target include at least:

[0032] Part or all of the obstacle target’s lateral position coordinates, longitudinal position coordinates, lateral speed, longitudinal speed, lateral acceleration, longitudinal acceleration, turn signal information, brake light information, and double flash warning light information.

[0033] In the second aspect, a target screening system based on a greedy algorithm is provided, comprising:

[0034] The validity screening module is used to screen the obstacles within the set range around the vehicle to obtain the validity screening target;

[0035] A sorting module, used to sort the effectiveness screening targets according to a predetermined sorting rule;

[0036] The target screening module is used to calculate the target screening coefficient of each effectiveness screening target in turn according to the sorting. If the target screening coefficient of the current effectiveness screening target is greater than a predetermined threshold, the scenario comprehensive screening coefficient is obtained based on the target screening coefficient of the current effectiveness screening target. Otherwise, the current effectiveness screening target is used as the final screening target, and the attributes of the final screening target are output.

[0037] In a third aspect, a vehicle is provided, comprising: a target screening system based on a greedy algorithm according to the second aspect.

[0038] In a fourth aspect, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps of the target screening method based on the greedy algorithm of the above-mentioned first aspect and any possible implementation method of the first aspect are implemented.

[0039] In a fifth aspect, a computer-readable storage medium is provided, on which a computer program is stored. When the program is executed by a processor, the steps of the target screening method based on the greedy algorithm in the above-mentioned first aspect and any possible implementation method of the first aspect are implemented.

[0040] In a sixth aspect, a computer program product is provided, on which a computer program is stored. When the program is executed by a processor, the steps of the target screening method based on the greedy algorithm in the above-mentioned first aspect and any possible implementation method of the first aspect are implemented.

[0041] By adopting the embodiment of the present application, the obstacles within a set range around the vehicle are screened for effectiveness to obtain effectiveness screening targets, and the effectiveness screening targets are sorted according to predetermined sorting rules. According to the sorting, the target screening coefficient of each effectiveness screening target is calculated in turn. If the target screening coefficient of the current effectiveness screening target is greater than a predetermined threshold, the scene comprehensive screening coefficient is obtained based on the target screening coefficient of the current effectiveness screening target. Otherwise, the current effectiveness screening target is used as the final screening target, and the attributes of the final screening target are output. In this way, target obstacle screening can be performed more accurately and efficiently while ensuring safety, thereby effectively improving driving comfort. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings:

[0043] Figure 1 A flowchart of a target screening method based on a greedy algorithm provided in an embodiment of the present application;

[0044] Figure 2 Another flow chart of the target screening method based on the greedy algorithm provided in the embodiment of the present application;

[0045] Figure 3 Schematic diagram of target screening in a cruising scenario;

[0046] Figure 4 A schematic diagram of the selection of targets in the cut-in and cut-out scenes;

[0047] Figure 5 A structural block diagram of a target screening system based on a greedy algorithm provided in an embodiment of the present application;

[0048] Figure 6 A structural block diagram of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0049] The present application is further described in detail below in conjunction with the embodiments and drawings. It is to be understood that the specific embodiments described herein are only used to explain the relevant application, rather than to limit the application. It is also necessary to explain that, for ease of description, only the parts related to the application are shown in the drawings.

[0050] It should be noted that, in the absence of conflict, the embodiments of the present application, that is, the features of the embodiments, can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0051] The following describes in detail the target screening method, system, device and medium based on the greedy algorithm according to the embodiments of the present application in conjunction with the accompanying drawings.

[0052] Figure 1 FIG. 1 is a flow chart of a target screening method based on a greedy algorithm according to an embodiment of the present application. Figure 1 As shown, the target screening method based on the greedy algorithm according to the embodiment of the present application includes the following steps:

[0053] S101: Perform effectiveness screening on obstacles within a set range around the vehicle to obtain effectiveness screening targets.

[0054] In one embodiment of the present application, obstacles within a set range around the vehicle are screened for effectiveness to obtain a effectiveness screening target, including: performing target recognition effectiveness judgment and recognition range effectiveness judgment on the obstacles within a set range around the vehicle to obtain a effectiveness screening target.

[0055] Combination Figure 2 As shown in the figure, all obstacle vehicles within the set range around the ego vehicle are screened for effectiveness. Validity includes target recognition effectiveness and recognition range effectiveness. Target recognition effectiveness includes target type recognition, target fusion recognition and target tracking recognition. Valid target types include four-wheeled vehicles, three-wheeled vehicles and two-wheeled vehicles. Valid target fusion types include radar camera fusion and single camera stable targets. Valid target tracking types include tracked and continuous tracking. The target recognition range is the target with the center line of the front bumper of the ego vehicle as the origin, the longitudinal range [0,200m], and the lateral range [-5.625m, 5.625m].

[0056] S102: Sort the effectiveness screening targets according to a predetermined sorting rule.

[0057] In one embodiment of the present application, the validity screening targets are sorted according to a predetermined sorting rule, including: sorting the validity screening targets according to the vertical position from near to far, wherein, when the vertical positions of any two validity screening targets are the same, the any two validity screening targets are sorted from left to right.

[0058] like Figure 2 As shown, the items are sorted from near to far in the vertical direction. If the vertical distances are the same, they are sorted in the order of left first and right later.

[0059] S103: According to the ranking, the target screening coefficient of each effectiveness screening target is calculated in turn.

[0060] In one embodiment of the present application, the target screening coefficient of each effectiveness screening target is calculated in sequence according to the ranking, including: calculating the driving comfort index ξ of each effectiveness screening target com 、Evasion convenience indexξ avo 、Collision loss indexξ loss and collision probability index ξ pro ; According to the driving comfort index ξ com 、Evasion convenience indexξ avo 、Collision loss indexξ loss and collision probability index ξ pro , and obtain the target screening coefficient for each effectiveness screening target.

[0061] Specifically, combined Figure 2As shown, for each obstacle object in the sorting, the target screening coefficient is calculated, and it is determined whether the target screening coefficient of the current object is greater than the set threshold.

[0062] The target screening coefficients include: driving comfort index ξ com 、Evasion convenience indexξ avo 、Collision loss indexξ loss and collision probability index ξ pro .

[0063] The calculation formula of driving comfort index is as follows:

[0064]

[0065] In the formula, δ s represents the steering wheel angle of the vehicle, Δδ s represents the steering wheel speed of the vehicle; a o Represents the longitudinal acceleration of the vehicle, v o Represents the longitudinal velocity of the vehicle.

[0066] The value range of the comfort index is [0,1]. When the calculation result exceeds this range, it is limited according to this range.

[0067] The calculation formula of the avoidance convenience index is as follows:

[0068]

[0069] In the formula, represents the road curvature, a o Represents the longitudinal acceleration of the vehicle, v o represents the longitudinal velocity of the vehicle, a e Represents the longitudinal acceleration value of the obstacle vehicle, v e Represents the longitudinal speed of the obstacle vehicle, S e Represents the longitudinal value of the obstacle vehicle in the SL coordinate system, L e Represents the lateral value of the obstacle vehicle in the SL coordinate system.

[0070] The value range of the avoidance convenience index is [0,1]. When the calculation result exceeds this range, it is limited according to this range.

[0071] The calculation formula of collision loss index is as follows:

[0072]

[0073] In the formula, represents the road curvature, v o Represents the longitudinal velocity of the vehicle, v e Represents the longitudinal velocity of the obstacle vehicle, Le Represents the lateral value of the obstacle vehicle in the SL coordinate system.

[0074] The value range of the collision loss index is [0,1]. When the calculated result exceeds this range, it is limited according to this range.

[0075] The calculation formula of collision probability index is as follows:

[0076]

[0077] In the formula, represents the road curvature, δ s represents the steering wheel angle of the vehicle, TTC represents the collision time, L e Represents the lateral value of the obstacle vehicle in the SL coordinate system.

[0078] The value range of the collision probability index is [0,1]. When the calculated result exceeds this range, it is limited according to this range.

[0079] The target screening coefficient calculation formula is:

[0080] ψ e =ξ com +ξ avo -ξ loss *ξ pro .

[0081] S104: If the target screening coefficient of the current validity screening target is greater than a predetermined threshold, the scenario comprehensive screening coefficient is obtained according to the target screening coefficient of the current validity screening target; otherwise, the current validity screening target is used as the final screening target, and the attributes of the final screening target are output.

[0082] In a specific example, the attributes of the final screening target include at least part or all of the obstacle target's lateral position coordinates, longitudinal position coordinates, lateral speed, longitudinal speed, lateral acceleration, longitudinal acceleration, turn signal information, brake light information, and double flash warning light information.

[0083] Among them, after the target screening coefficient of the current validity screening target is greater than a predetermined threshold, and the scene comprehensive screening coefficient is obtained based on the target screening coefficient of the current validity screening target, it also includes: judging whether the scene comprehensive screening coefficient is greater than the predetermined threshold; if not, taking the current validity screening target as the final screening target, and outputting the attributes of the final screening target.

[0084] Specifically, the current target screening coefficient is added to the scene comprehensive screening coefficient to obtain the latest scene comprehensive screening coefficient.

[0085] The scenario screening coefficient calculation formula is:

[0086]

[0087] Typical application scenarios of the target screening method based on the greedy algorithm in the embodiment of the present application are as follows:

[0088] like Figure 3 As shown, according to the traditional screening algorithm, obstacle car 2 will be screened as the target obstacle in the cruising scene. However, according to the habits of human drivers, obstacle car 4 should be screened as the target obstacle because obstacle cars 2 and 3 are easy to avoid by steering.

[0089] like Figure 4 As shown in the figure below, the screening of targets in the cut-in and cut-out scenarios is as follows: obstacle car 2 is cutting-out from the lane to the left lane, obstacle car 3 is cutting-in from the right lane to the lane, and obstacle car 4 is going straight. According to the traditional screening algorithm, obstacle car 2 will be screened as a target obstacle. However, according to the habits of human drivers, obstacle car 3 should be screened as a potential dangerous target obstacle, and obstacle 4 as an alternative target obstacle. Because obstacle car 2 is easy to avoid by steering.

[0090] According to the target screening method based on the greedy algorithm of the embodiment of the present application, the obstacles within the set range around the vehicle are screened for effectiveness to obtain effectiveness screening targets, and the effectiveness screening targets are sorted according to predetermined sorting rules. According to the sorting, the target screening coefficient of each effectiveness screening target is calculated in turn. If the target screening coefficient of the current effectiveness screening target is greater than a predetermined threshold, the scene comprehensive screening coefficient is obtained according to the target screening coefficient of the current effectiveness screening target. Otherwise, the current effectiveness screening target is used as the final screening target, and the attributes of the final screening target are output. In this way, target obstacle screening can be performed more accurately and efficiently while ensuring safety, thereby effectively improving driving comfort.

[0091] Figure 5 is a structural block diagram of a target screening system based on a greedy algorithm according to an embodiment of the present application. Figure 5 As shown, according to an embodiment of the present application, a target screening system based on a greedy algorithm includes: a validity screening module 510, a sorting module 520 and a target screening module 530, wherein:

[0092] The validity screening module 510 is used to screen the obstacles within a set range around the vehicle to obtain a validity screening target;

[0093] A sorting module 520 is used to sort the effectiveness screening targets according to a predetermined sorting rule;

[0094] The target screening module 530 is used to calculate the target screening coefficient of each validity screening target in turn according to the sorting. If the target screening coefficient of the current validity screening target is greater than a predetermined threshold, the scenario comprehensive screening coefficient is obtained based on the target screening coefficient of the current validity screening target. Otherwise, the current validity screening target is used as the final screening target, and the attributes of the final screening target are output.

[0095] According to the target screening system based on the greedy algorithm of the embodiment of the present application, the obstacles within the set range around the vehicle are screened for effectiveness to obtain effectiveness screening targets, and the effectiveness screening targets are sorted according to predetermined sorting rules. According to the sorting, the target screening coefficient of each effectiveness screening target is calculated in turn. If the target screening coefficient of the current effectiveness screening target is greater than the predetermined threshold, the scene comprehensive screening coefficient is obtained according to the target screening coefficient of the current effectiveness screening target. Otherwise, the current effectiveness screening target is used as the final screening target, and the attributes of the final screening target are output. In this way, target obstacle screening can be performed more accurately and efficiently while ensuring safety, thereby effectively improving driving comfort.

[0096] For the specific definition of the target screening system based on the greedy algorithm, please refer to the definition of the target screening method based on the greedy algorithm above, which will not be repeated here. The various modules of the target screening system based on the greedy algorithm can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned various modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0097] In one embodiment, a vehicle is provided, comprising: a target screening system based on a greedy algorithm according to any of the above embodiments. The vehicle performs effectiveness screening on obstacles within a set range around the vehicle to obtain effectiveness screening targets, sorts the effectiveness screening targets according to a predetermined sorting rule, and calculates the target screening coefficient of each effectiveness screening target in turn according to the sorting. If the target screening coefficient of the current effectiveness screening target is greater than a predetermined threshold, the scene comprehensive screening coefficient is obtained according to the target screening coefficient of the current effectiveness screening target. Otherwise, the current effectiveness screening target is used as the final screening target, and the attributes of the final screening target are output. Thus, the target obstacle screening can be performed more accurately and efficiently under the premise of ensuring safety, effectively improving driving comfort.

[0098] In addition, other structures and functions of the vehicle according to the embodiment of the present application are known to ordinary technicians in the field and will not be elaborated here.

[0099] In one embodiment, a computer device is provided. Figure 6 This is a block diagram of the computer device provided in the embodiment of the present application, refer to Figure 6 The computer device includes a memory and a processor. The memory stores a computer program. When the processor executes the computer program, the aforementioned target screening method embodiment based on the greedy algorithm is implemented. For example, the following is performed: screening the effectiveness of obstacles within a set range around the vehicle to obtain a validity screening target;

[0100] Sorting the effectiveness screening targets according to predetermined sorting rules;

[0101] According to the ranking, the target screening coefficient of each effectiveness screening target is calculated in turn;

[0102] If the target screening coefficient of the current validity screening target is greater than a predetermined threshold, the scenario comprehensive screening coefficient is obtained based on the target screening coefficient of the current validity screening target; otherwise, the current validity screening target is used as the final screening target, and the attributes of the final screening target are output.

[0103] The embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. When the processor executes the computer program, the aforementioned target screening method embodiment based on the greedy algorithm is implemented. For example, the following is performed: screening the effectiveness of obstacles within a set range around the vehicle to obtain a validity screening target;

[0104] Sorting the effectiveness screening targets according to predetermined sorting rules;

[0105] According to the ranking, the target screening coefficient of each effectiveness screening target is calculated in turn;

[0106] If the target screening coefficient of the current validity screening target is greater than a predetermined threshold, the scenario comprehensive screening coefficient is obtained based on the target screening coefficient of the current validity screening target; otherwise, the current validity screening target is used as the final screening target, and the attributes of the final screening target are output.

[0107] The present application embodiment provides a computer program product, which includes instructions. When the instructions are executed, the method described in the embodiment of the present application is executed. For example, it can be executed Figure 1 The various steps of the target screening method based on the greedy algorithm shown, for example, are performed: performing effectiveness screening on obstacles within a set range around the vehicle to obtain effectiveness screening targets;

[0108] Sorting the effectiveness screening targets according to predetermined sorting rules;

[0109] According to the ranking, the target screening coefficient of each effectiveness screening target is calculated in turn;

[0110] If the target screening coefficient of the current validity screening target is greater than a predetermined threshold, the scenario comprehensive screening coefficient is obtained based on the target screening coefficient of the current validity screening target; otherwise, the current validity screening target is used as the final screening target, and the attributes of the final screening target are output.

[0111] Those of ordinary skill in the art can understand that all or part of the processes in the methods for implementing the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0112] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0113] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the patent application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent application shall be subject to the attached claims.

Claims

1. A target screening method based on a greedy algorithm, characterized in that: include: Perform effectiveness screening on obstacles within a set range around the vehicle to obtain effectiveness screening targets; Sorting the effectiveness screening targets according to predetermined sorting rules; According to the ranking, the target screening coefficient of each effectiveness screening target is calculated in turn; If the target screening coefficient of the current validity screening target is greater than a predetermined threshold, the scenario comprehensive screening coefficient is obtained based on the target screening coefficient of the current validity screening target; otherwise, the current validity screening target is used as the final screening target, and the attributes of the final screening target are output.

2. The target screening method based on the greedy algorithm according to claim 1, characterized in that: The effectiveness screening of obstacles within a set range around the vehicle to obtain an effectiveness screening target includes: The effectiveness of target recognition and recognition range is judged for obstacles within the set range around the vehicle to obtain effectiveness screening targets.

3. The target screening method based on the greedy algorithm according to claim 1, characterized in that: The sorting of the effectiveness screening targets according to a predetermined sorting rule includes: The validity screening targets are sorted according to their longitudinal positions from near to far, wherein when the longitudinal positions of any two validity screening targets are the same, the said any two validity screening targets are sorted from left to right first.

4. The target screening method based on the greedy algorithm according to claim 1, characterized in that: The target screening coefficient of each effectiveness screening target is calculated in sequence according to the ranking, including: Calculate the driving comfort index ξ for each effectiveness screening target com 、Evasion convenience indexξ avo 、Collision loss indexξ loss and collision probability index ξ pro ; According to the driving comfort index ξ com 、Evasion convenience indexξ avo , collision loss index ξ loss and collision probability index ξ pro , and obtain the target screening coefficient for each effectiveness screening target.

5. The target screening method based on the greedy algorithm according to claim 4 is characterized in that: The driving comfort index calculation formula is: Among them, δ s represents the steering wheel angle of the vehicle, Δδ s represents the steering wheel speed of the vehicle; a o Represents the longitudinal acceleration of the vehicle, v o Represents the longitudinal velocity value of the vehicle; The calculation formula of the avoidance convenience index is: in, represents the road curvature, a o Represents the longitudinal acceleration of the vehicle, v o represents the longitudinal velocity of the vehicle, a e Represents the longitudinal acceleration value of the obstacle vehicle, v e Represents the longitudinal speed of the obstacle vehicle, S e Represents the longitudinal value of the obstacle vehicle in the SL coordinate system, L e Represents the lateral value of the obstacle vehicle in the SL coordinate system; The calculation formula of collision loss index is: in, represents the road curvature, v o Represents the longitudinal velocity of the vehicle, v e Represents the longitudinal velocity of the obstacle vehicle, L e Represents the lateral value of the obstacle vehicle in the SL coordinate system; The calculation formula of collision probability index is: in, represents the road curvature, δ s represents the steering wheel angle of the vehicle, TTC represents the collision time, L e Represents the lateral value of the obstacle vehicle in the SL coordinate system.

6. The target screening method based on the greedy algorithm according to claim 1, characterized in that: After the target screening coefficient of the current validity screening target is greater than a predetermined threshold and the scenario comprehensive screening coefficient is obtained according to the target screening coefficient of the current validity screening target, the following further includes: Determining whether the scene comprehensive screening coefficient is greater than the predetermined threshold; If not, the current validity screening target is used as the final screening target, and the attributes of the final screening target are output.

7. The target screening method based on the greedy algorithm according to any one of claims 1 to 6, characterized in that: The attributes of the final screening target include at least: Part or all of the obstacle target’s lateral position coordinates, longitudinal position coordinates, lateral speed, longitudinal speed, lateral acceleration, longitudinal acceleration, turn signal information, brake light information, and double flash warning light information.

8. A target screening system based on a greedy algorithm, characterized in that: include: The validity screening module is used to screen the obstacles within the set range around the vehicle to obtain the validity screening target; A sorting module, used to sort the effectiveness screening targets according to a predetermined sorting rule; The target screening module is used to calculate the target screening coefficient of each effectiveness screening target in turn according to the sorting. If the target screening coefficient of the current effectiveness screening target is greater than a predetermined threshold, the scenario comprehensive screening coefficient is obtained based on the target screening coefficient of the current effectiveness screening target. Otherwise, the current effectiveness screening target is used as the final screening target, and the attributes of the final screening target are output.

9. A vehicle, characterized in that: include: The target screening system based on the greedy algorithm according to claim 8.

10. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the target screening method based on the greedy algorithm according to any one of claims 1 to 7 is implemented.

Images