Method and device for determining cut-in target concerned by vehicle and medium

Abstract

The invention provides a method and device for determining a cut-in target concerned by a vehicle and a medium. The method comprises the steps that map data, road data and obstacle data are acquired through a vehicle-mounted sensor; fusing the map data, the road data and the obstacle data to determine a first obstacle in a lane adjacent to the lane where the vehicle is located; determining the cut-in duration of the first obstacle according to the obstacle data; according to the cut-in duration and the obstacle data, determining a predicted position where the first obstacle is located after the first obstacle runs towards the lane where the vehicle is located for the cut-in duration; according to the position relation between the predicted position and the lane where the vehicle is located, the cut-in probability that the first obstacle cuts in the lane where the vehicle is located is determined; and according to the cut-in probability and a preset probability threshold, determining whether the first obstacle is a target obstacle to which the vehicle needs to pay attention. The objective of the invention is to accurately and efficiently predict a target obstacle which needs to be concerned by a vehicle and will affect automatic driving of the vehicle in advance from a plurality of obstacles in a specified range of a current road.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle engineering, and particularly to a method, device and medium for determining a cut-in target that the host vehicle is concerned about. Background Art

[0002] In the field of autonomous driving, identifying and analyzing obstacles that the host vehicle needs to pay attention to to prevent the vehicle from colliding with the obstacle during autonomous driving is one of the key factors determining whether the autonomous driving control is good. The existing method for identifying and analyzing obstacles around the vehicle to determine the obstacles that the host vehicle needs to pay attention to is mainly based on the lane lines of the lane where the vehicle is located, and selecting the obstacles whose wheels cross the lane lines of the lane where the vehicle is located during driving as the obstacle areas that the host vehicle needs to pay attention to.

[0003] However, this method has a high false detection rate and is prone to misidentifying obstacles that the host vehicle does not need to pay attention to as obstacles that the host vehicle needs to pay attention to. For example, when an obstacle just crosses the lane lines of the lane where the vehicle is located, but the obstacle does not hinder the driving of the vehicle and there is no possibility that the driving trajectory of the obstacle cuts into the lane where the vehicle is located, the obstacle will also be identified by the host vehicle as an obstacle that needs to be paid attention to, resulting in false detection. At the same time, since an obstacle is determined to be an obstacle that the host vehicle needs to pay attention to only when it has crossed the lane lines of the lane where the vehicle is located, it is impossible to predict in advance whether an obstacle is an obstacle that the host vehicle needs to pay attention to based on the driving data information of the obstacle before it crosses the lane lines of the lane where the vehicle is located. Summary of the Invention

[0004] In view of this, the present invention provides a method, device and medium for determining a cut-in target that the host vehicle is concerned about, aiming to accurately and efficiently predict in advance from multiple obstacles within a specified range of the current road the target obstacles that will affect the autonomous driving of the host vehicle and that the host vehicle needs to pay attention to.

[0005] To achieve the above object, the technical solution of the present invention is realized as follows:

[0006] A method for determining a cut-in target that the host vehicle is concerned about, the method comprising:

[0007] Obtaining map data, road data and obstacle data through in-vehicle sensors;

[0008] Fusing the map data, the road data and the obstacle data to determine a first obstacle in an adjacent lane of the lane where the host vehicle is located from the obstacles on the current road;

[0009] Determining the cut-in duration of the first obstacle from its current position into the lane where the host vehicle is located according to the obstacle type in the obstacle data and the position of the obstacle relative to the host vehicle;

[0010] Based on the cut-in duration, the lateral driving speed of the obstacle in the obstacle data, and the position of the obstacle relative to the host vehicle, determine the predicted position of the first obstacle when it is in the process of cutting into the lane where the host vehicle is located after traveling for the cut-in duration.

[0011] Based on the positional relationship between the predicted position and the lane where the host vehicle is located, determine the cut-in probability of the first obstacle cutting into the lane where the host vehicle is located.

[0012] Based on the cut-in probability and a preset probability threshold, determine whether the first obstacle is a target obstacle that the host vehicle needs to pay attention to.

[0013] Further, the step of fusing the map data, the road data, and the obstacle data to determine a first obstacle in the adjacent lane of the lane where the host vehicle is located from the obstacles on the current road includes:

[0014] Perform road fusion on the map data and the road data to obtain lane parameter information of the current road.

[0015] Perform perception fusion on the lane parameter information and the obstacle data to determine a first obstacle in the adjacent lane of the lane where the host vehicle is located from the obstacles on the current road.

[0016] Further, the step of determining the cut-in duration of the first obstacle cutting into the lane where the host vehicle is located from its current position according to the obstacle type in the obstacle data and the position of the obstacle relative to the host vehicle includes:

[0017] According to the obstacle type in the obstacle data of the first obstacle, determine an initial cut-in duration corresponding to the obstacle type of the first obstacle.

[0018] According to the longitudinal distance between the first obstacle and the host vehicle and the obstacle type of the first obstacle, correct the initial cut-in duration to obtain the cut-in duration of the first obstacle cutting into the lane where the host vehicle is located from its current position.

[0019] Further, the step of correcting the initial cut-in duration according to the longitudinal distance between the first obstacle and the host vehicle and the obstacle type of the first obstacle to obtain the cut-in duration of the first obstacle cutting into the lane where the host vehicle is located from its current position includes:

[0020] According to the obstacle type of the first obstacle, determine a target correction strategy, where the target correction strategy represents the corresponding relationship between the longitudinal distance between the first obstacle of this obstacle type and the host vehicle and a first correction coefficient.

[0021] Determine a first correction coefficient according to the longitudinal distance between the first obstacle and the host vehicle and the target correction strategy.

[0022] Determine the cut-in duration for the first obstacle to cut into the lane where the host vehicle is located from its current position by multiplying the first correction coefficient by the initial cut-in duration.

[0023] Further, the step of determining the cut-in duration for the first obstacle to cut into the lane where the host vehicle is located from its current position by multiplying the first correction coefficient by the initial cut-in duration includes:

[0024] Determine the corrected cut-in duration by multiplying the first correction coefficient by the initial cut-in duration.

[0025] Determine a second correction coefficient corresponding to the target driving style according to the target driving style of the host vehicle selected by the user, and perform a secondary correction on the corrected cut-in duration based on the second correction coefficient to obtain the cut-in duration for the first obstacle to cut into the lane where the host vehicle is located from its current position.

[0026] Further, the step of determining the predicted position of the first obstacle after traveling the cut-in duration during the process of cutting into the lane where the host vehicle is located according to the cut-in duration, the lateral driving speed of the obstacle in the obstacle data, and the position of the obstacle relative to the host vehicle includes:

[0027] Determine the initial predicted position of the first obstacle after traveling the cut-in duration during the process of cutting into the lane where the host vehicle is located according to the cut-in duration and the lateral driving speed of the first obstacle in the obstacle data, and according to the lateral distance between the first obstacle and the host vehicle.

[0028] Correct the initial predicted position according to the obstacle size and the obstacle heading angle in the obstacle data of the first obstacle to obtain the predicted position of the first obstacle after traveling the cut-in duration during the process of cutting into the lane where the host vehicle is located.

[0029] Further, the step of determining the cut-in probability of the first obstacle cutting into the lane where the host vehicle is located according to the positional relationship between the predicted position and the lane where the host vehicle is located includes:

[0030] Determine a target probability strategy corresponding to the obstacle type according to the obstacle type of the first obstacle, where the target probability strategy represents the corresponding relationship between the distance between the center line of the first obstacle under this obstacle type and the center line of the lane where the host vehicle is located and the cut-in probability.

[0031] Determine the distance between the center line of the first obstacle and the center line of the lane where the host vehicle is located according to the predicted position;

[0032] Determine the cut-in probability of the first obstacle cutting into the lane where the host vehicle is located according to the distance and the target probability strategy.

[0033] Further, the determining whether the first obstacle is a target obstacle that the host vehicle needs to pay attention to according to the cut-in probability and a preset probability threshold includes:

[0034] Determine a target probability threshold corresponding to the obstacle type of the first obstacle according to the obstacle type of the first obstacle;

[0035] When the cut-in probability exceeds the target probability threshold, determine that the first obstacle is a target obstacle that the host vehicle needs to pay attention to.

[0036] A method for determining a cut-in target that the host vehicle pays attention to according to the present invention has the following advantages:

[0037] First, by fusing a variety of data information, it is possible to more accurately determine the obstacles in the two adjacent lanes of the lane where the host vehicle is located from the obstacles on the current road. And subsequently, when determining whether an obstacle is an obstacle that the host vehicle needs to pay attention to, only the obstacles in the two adjacent lanes of the lane where the host vehicle is located are determined, and other obstacles on the current road are no longer concerned, so the determination efficiency can be effectively improved.

[0038] Secondly, through the relevant driving data of the obstacle, predict the predicted position of the obstacle after driving for the cut-in duration calculated for the obstacle. According to the positional relationship between the predicted position and the lane where the host vehicle is located, predict in advance whether the obstacle is a target obstacle that the host vehicle needs to pay attention to. Thus, it can be estimated in advance whether the obstacle is a target obstacle that the host vehicle needs to pay attention to, and in this way, it is possible to more proactively determine the obstacles that the host vehicle needs to pay attention to to ensure the safe driving of the host vehicle.

[0039] Another object of the present invention is to propose a device for determining a cut-in target that the host vehicle pays attention to. The purpose is to accurately and efficiently predict in advance from multiple obstacles within a specified range of the current road the target obstacles that will affect the autonomous driving of the host vehicle and that the host vehicle needs to pay attention to.

[0040] To achieve the above object, the technical solution of the present invention is implemented as follows:

[0041] A device for determining a cut-in target that the host vehicle pays attention to, the device includes:

[0042] A data acquisition module, configured to acquire map data, road data, and obstacle data;

[0043] The first obstacle determination module is configured to fuse the map data, the road data, and the obstacle data to determine a first obstacle in an adjacent lane of the lane where the host vehicle is located from the obstacles on the current road.

[0044] The cut-in duration determination module is configured to determine the cut-in duration for the first obstacle to cut into the lane where the host vehicle is located from its current position according to the obstacle type in the obstacle data and the position of the obstacle relative to the host vehicle.

[0045] The position prediction module is configured to determine the predicted position where the first obstacle is located after traveling the cut-in duration during the process of cutting into the lane where the host vehicle is located according to the cut-in duration, the lateral traveling speed of the obstacle in the obstacle data, and the position of the obstacle relative to the host vehicle.

[0046] The cut-in probability calculation module is configured to determine the cut-in probability of the first obstacle cutting into the lane where the host vehicle is located according to the positional relationship between the predicted position and the lane where the host vehicle is located.

[0047] The target obstacle determination module is configured to determine whether the first obstacle is a target obstacle that the host vehicle needs to pay attention to according to the cut-in probability and a preset probability threshold.

[0048] The device for determining the cut-in target that the host vehicle pays attention to has the same advantages as the above-mentioned method for determining the cut-in target that the host vehicle pays attention to compared with the prior art, and will not be elaborated here.

[0049] Another object of the present invention is to provide a vehicle, aiming to accurately and efficiently predict in advance a target obstacle that the host vehicle needs to pay attention to and that will affect the autonomous driving of the host vehicle from multiple obstacles within a specified range on the current road.

[0050] To achieve the above object, the technical solution of the present invention is implemented as follows:

[0051] A vehicle includes: the above-mentioned device for determining the cut-in target that the host vehicle pays attention to, and is configured to execute the steps in the above-mentioned method for determining the cut-in target that the host vehicle pays attention to.

[0052] The vehicle has the same advantages as the above-mentioned device for determining the cut-in target that the host vehicle pays attention to compared with the prior art, and will not be elaborated here.

[0053] Another object of the present invention is to provide a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps in the above-mentioned method for determining the cut-in target that the host vehicle pays attention to are implemented. Description of the Drawings

[0054] The accompanying drawings, which form a part of the present invention, are used to provide a further understanding of the present invention. The schematic embodiments and descriptions thereof of the present invention are used to explain the present invention and do not constitute an improper limitation to the present invention. In the drawings:

[0055] Figure 1 is a flowchart of a method for determining a cut-in target of interest to a host vehicle shown in an embodiment of the present application;

[0056] Figure 2 is a schematic diagram of the position setting of in-vehicle sensors in a method for determining a cut-in target of interest to a host vehicle shown in an embodiment of the present application;

[0057] Figure 3 is a schematic diagram of road data in a method for determining a cut-in target of interest to a host vehicle shown in an embodiment of the present application;

[0058] Figure 4 is a schematic diagram of a target correction strategy in a method for determining a cut-in target of interest to a host vehicle shown in an embodiment of the present application;

[0059] Figure 5 is a schematic diagram of a target probability strategy in a method for determining a cut-in target of interest to a host vehicle shown in an embodiment of the present application;

[0060] Figure 6 is a schematic diagram of a device for determining a cut-in target of interest to a host vehicle shown in an embodiment of the present application. Detailed implementation manners

[0061] It should be noted that, without conflict, the embodiments in the present invention and the features in the embodiments may be combined with each other.

[0062] The present invention will be described in detail below with reference to the accompanying drawings and in combination with embodiments.

[0063] Figure 1 is a flowchart of a method for determining a cut-in target of interest to a host vehicle shown in an embodiment of the present application. Referring to Figure 1 , a method for determining a cut-in target of interest to a host vehicle provided by the present application includes the following steps:

[0064] Step S11: Obtain map data, road data, and obstacle data through in-vehicle sensors;

[0065] Step S12: Fuse the map data, the road data, and the obstacle data to determine a first obstacle in an adjacent lane of the lane where the host vehicle is located from the obstacles on the current road;

[0066] Step S13: Determine the cut-in duration for the first obstacle to cut into the lane where the host vehicle is located from its current position according to the obstacle type in the obstacle data and the position of the obstacle relative to the host vehicle.

[0067] Step S14: Determine the predicted position where the first obstacle is located after traveling for the cut-in duration during the process of cutting into the lane where the host vehicle is located according to the cut-in duration, the lateral driving speed of the obstacle in the obstacle data, and the position of the obstacle relative to the host vehicle.

[0068] Step S15: Determine the cut-in probability of the first obstacle cutting into the lane where the host vehicle is located according to the position relationship between the predicted position and the lane where the host vehicle is located.

[0069] Step S16: Determine whether the first obstacle is a target obstacle that the host vehicle needs to pay attention to according to the cut-in probability and a preset probability threshold.

[0070] In this embodiment, map data in the current road is obtained through the in-vehicle navigation map in the host vehicle. Road data within a preset range in front of the current road of the host vehicle is collected by in-vehicle sensors configured in the host vehicle, including lane lines and lane line types in the current road. Obstacles around the host vehicle body are collected by other in-vehicle sensors configured in the host vehicle to obtain obstacle data. Among them, each in-vehicle sensor preferably selects all-weather sensor detection equipment to avoid unstable object target detection caused by rain, snow, fog, light, etc., so as to prevent inaccurate data collection.

[0071] In this embodiment, the obstacle data includes: obstacle type, position information of the obstacle relative to the host vehicle, lateral driving speed of the obstacle, obstacle size, obstacle heading angle, etc. And the in-vehicle sensors for collecting obstacles around the host vehicle body are not limited to being set at the middle position directly in front of the host vehicle body, nor are they limited to only setting 1. To improve the accuracy of object detection, radar sensors (such as lidar or millimeter-wave radar equipment, etc.) and vision sensors can be arranged in front of and on the sides of the vehicle. At the same time, two corner radar devices can be installed at the two left and right corner positions in front of the vehicle to reduce the occurrence of misdetection and missed detection of object targets through equipment redundancy.

[0072] Figure 2 It is a schematic diagram of the position setting of in-vehicle sensors in a method for determining a cut-in target that the host vehicle pays attention to shown in an embodiment of the present application. Refer to Figure 2 , 21 is the in-vehicle sensor for collecting road data within a preset range in front of the current road of the host vehicle; 22 is the in-vehicle sensor for collecting obstacle data of obstacles around the host vehicle body; 23 is the control unit for receiving information from different sensors and sending control information to the vehicle.

[0073] After collecting map data, road data, and obstacle data of the host vehicle in step S11, in step S12, the map data, road data, and obstacle data are fused to determine the obstacles in the left and right adjacent lanes of the host vehicle's lane among the obstacles on the current road, which are called the first obstacles. It should be understood that the obstacles in the left and right adjacent lanes of the host vehicle's lane include one or more.

[0074] In this embodiment, after determining the first obstacle, according to the obstacle type in the obstacle data belonging to the first obstacle, the obstacle type to which the first obstacle belongs can be determined. According to the obstacle type of the first obstacle, the cut-in duration for the first obstacle corresponding to the obstacle type to cut into the host vehicle's lane from its current position is determined.

[0075] In this embodiment, the obstacle types include: household cars (such as sedans, SUVs, etc.), trucks, motorcycles, bicycles, pedestrians, etc. By configuring corresponding cut-in durations for different types of obstacles. According to the obstacle type of the first obstacle, the cut-in duration for the first obstacle to cut into the host vehicle's lane from its current position can be determined.

[0076] According to the cut-in duration, the lateral driving speed of the obstacle data belonging to the first obstacle, and the position of the first obstacle relative to the host vehicle, after the first obstacle cuts into the host vehicle's lane for the cut-in duration, the position where the first obstacle is located, that is, the predicted position, can be calculated.

[0077] According to the positional relationship between the predicted position of the first obstacle obtained by prediction and the host vehicle's lane, the cut-in probability of the first obstacle cutting into the host vehicle's lane can be determined. The greater the cut-in probability, the greater the probability that the first obstacle cuts into the host vehicle's lane in its current driving state; the smaller the cut-in probability, the smaller the probability that the first obstacle cuts into the host vehicle's lane in its current driving state.

[0078] By comparing the cut-in probability of the first obstacle cutting into the host vehicle's lane with a preset probability threshold. When the cut-in probability exceeds the preset probability threshold, the first obstacle is very likely to cut into the host vehicle's lane, so the first obstacle is determined to be the target obstacle that the host vehicle needs to pay attention to.

[0079] A method for determining a cut-in target of interest to the host vehicle can, by fusing various data information, more accurately determine obstacles in the two adjacent lanes of the lane where the host vehicle is located from the obstacles on the current road. And subsequently, when determining whether an obstacle is an obstacle of interest to the host vehicle, only the obstacles in the two adjacent lanes of the lane where the host vehicle is located are determined, and other obstacles on the current road are no longer concerned. Therefore, the determination efficiency can be effectively improved.

[0080] And based on the relevant driving data of the obstacle, predict the predicted position of the obstacle after driving for the cut-in duration calculated for the obstacle. According to the positional relationship between the predicted position and the lane where the host vehicle is located, predict in advance whether the obstacle is a target obstacle that the host vehicle needs to pay attention to. Thus, it can be predicted in advance whether the obstacle is a target obstacle that the host vehicle needs to pay attention to, so as to more proactively determine the obstacles that the host vehicle needs to pay attention to to ensure the safe driving of the host vehicle.

[0081] In this application, step S11 specifically includes:

[0082] Step S111: Perform road fusion on the map data and the road data to obtain the lane parameter information of the current road;

[0083] Step S112: Perform perception fusion on the lane parameter information and the obstacle data to determine a first obstacle in the adjacent lane of the lane where the host vehicle is located from the obstacles on the current road.

[0084] In this embodiment, the road data in a preset range in front of the current road of the host vehicle is collected by an in-vehicle sensor configured on the host vehicle, including lane lines, lane line types, etc. in the current road. Since this application only focuses on the lane where the host vehicle is located, as well as the left adjacent lane and the right adjacent lane of the lane where the host vehicle is located. Therefore, to save computing resources, only the road data of the lane where the host vehicle is located and the two adjacent lanes is collected when collecting road data. At the same time, since the host vehicle only needs to pay attention to obstacles within a certain length range in front during the automatic driving process, and the host vehicle does not need to pay attention to obstacles that are very far from the host vehicle. Therefore, to save computing resources, only the road data in the preset range in front is collected when collecting road data resources.

[0085] Exemplarily, Figure 3 is a schematic diagram of road data in a method for determining a cut-in target of interest to the host vehicle shown in an embodiment of this application. Refer to Figure 3, road data within a preset range ahead is collected by on-vehicle sensors. Preferably, the preset range is the road data within 120 m ahead of the host vehicle. The road data includes the left lane line LL of the left adjacent lane of the host vehicle's lane, the right lane line of the left adjacent lane of the host vehicle's lane (which is also the left lane line LR of the host vehicle's lane), the right lane line RR of the right adjacent lane of the host vehicle's lane, and the left lane line of the right adjacent lane of the host vehicle's lane (which is also the right lane line RL of the host vehicle's lane). And the lane line types of these lane lines, such as dotted lines, double solid lines, single solid lines, etc.

[0086] In this embodiment, by performing road fusion on the map data of the host vehicle and the collected road data, lane parameter information within the preset range of the current road is obtained, including lane line position information, lane width information, lane curvature information, lane line type information, etc. within the preset range ahead of the host vehicle.

[0087] By performing perception fusion on the lane parameter information obtained through road fusion and the obtained obstacle data, the first obstacle in the two adjacent lanes of the host vehicle's lane can be determined. Subsequently, it is only necessary to determine whether each first obstacle is a target obstacle that the host vehicle needs to pay attention to, and obstacles in other lanes do not need to be considered, thus effectively saving computing resources.

[0088] In this application, step S12 specifically includes:

[0089] Step S121: Determine the initial cut-in duration corresponding to the obstacle type of the first obstacle according to the obstacle type in the obstacle data of the first obstacle;

[0090] Step S122: Modify the initial cut-in duration according to the longitudinal distance between the first obstacle and the host vehicle and the obstacle type of the first obstacle to obtain the cut-in duration for the first obstacle to cut into the host vehicle's lane from its current position.

[0091] In this embodiment, corresponding initial cut-in durations are configured for obstacles of different obstacle types. The obstacle type and the initial cut-in duration are in one-to-one correspondence. According to the obstacle type of the first obstacle in the obstacle data, the initial cut-in duration corresponding to this obstacle type can be obtained.

[0092] Exemplarily, the obstacle types include household cars, trucks, motorcycles, bicycles, and pedestrians. The corresponding initial cut-in duration of 1.25S is configured for the household car obstacle type; the corresponding initial cut-in duration of 1.5S is configured for the truck obstacle type; the corresponding initial cut-in time of 1S is configured for obstacle types such as motorcycles, bicycles, and pedestrians. According to the obstacle type of the first obstacle, the initial cut-in duration of the first obstacle can be determined. The initial cut-in duration is configured for the first obstacle and is used to predict the predicted position where the first obstacle will travel after traveling such an initial cut-in duration during the process of cutting into the lane where the host vehicle is located. This initial cut-in duration is not the duration required for the first obstacle to cut into the center position of the lane where the host vehicle is located from the current position of the host vehicle.

[0093] Since when the first obstacle has the intention of cutting into the lane where the host vehicle is located, if the distance between the first obstacle and the host vehicle is smaller, in order to avoid colliding with the host vehicle during the cut-in, the first obstacle will cut into the lane where the host vehicle is located in a more aggressive and rapid manner. Therefore, for the first obstacle, using a fixed initial cut-in duration to predict the predicted position where the first obstacle will travel after traveling such an initial cut-in duration during the process of cutting into the lane where the host vehicle is located will result in an inaccurate final prediction result.

[0094] Therefore, after determining the initial cut-in duration corresponding to the obstacle type of the first obstacle according to the obstacle type in the obstacle data of the first obstacle. Then, according to the longitudinal distance between the first obstacle and the host vehicle and the obstacle type of the first obstacle, the initial cut-in duration configured for the first obstacle of this obstacle type is corrected to ensure a more accurate prediction result.

[0095] In this application, step S122 specifically includes:

[0096] Step S1221: According to the obstacle type of the first obstacle, determine the target correction strategy corresponding to the obstacle type, and the target correction strategy represents the corresponding relationship between the longitudinal distance between the first obstacle of this obstacle type and the host vehicle and the first correction coefficient;

[0097] Step S1222: According to the longitudinal distance between the first obstacle and the host vehicle and the target correction strategy, determine the first correction coefficient;

[0098] Step S1223: Determine the cut-in duration for the first obstacle to cut into the lane where the host vehicle is located from its current position by multiplying the first correction coefficient by the initial cut-in duration.

[0099] In this embodiment, since the driving states of obstacles of different obstacle types are different. For example, a household car has a faster driving speed and a shorter braking time; while a truck has a slower driving speed and a longer braking time; for obstacle types such as motorcycles, bicycles, and pedestrians, although their driving speeds are relatively slow, their movements are more flexible. Therefore, correcting the initial cut-in duration in a correction manner corresponding to the obstacle type can ensure more accurate correction of the initial cut-in duration of the first obstacle of different obstacle types. Therefore, a corresponding target correction strategy is configured for each obstacle type, and the obstacle type and the target correction strategy are in one-to-one correspondence. The target correction strategy corresponding to the obstacle type represents the corresponding relationship between the longitudinal distance between the first obstacle of this obstacle type and the host vehicle and the first correction coefficient, that is, the corresponding relationship between this longitudinal distance and the first correction coefficient.

[0100] According to the obstacle type of the first obstacle, the target correction strategy corresponding to this obstacle type can be determined. According to the position of the first obstacle relative to the host vehicle in the obstacle data of this first obstacle, the longitudinal distance between this first obstacle and the host vehicle can be determined. By querying in this target correction strategy, the first correction coefficient corresponding to this longitudinal distance in this target correction strategy can be determined. By multiplying the initial cut-in duration of this first obstacle by the determined first correction coefficient, the cut-in duration for this first obstacle to cut into the lane where the host vehicle is located from its current position is obtained.

[0101] Exemplarily, Figure 4 is a schematic diagram of the target correction strategy in a method for determining a cut-in target concerned by the host vehicle shown in an embodiment of the present application. Referring to Figure 4 , K represents the first correction coefficient, and dx represents the longitudinal distance between the first obstacle and the host vehicle. According to the obstacle type of the first obstacle, the target correction strategy corresponding to this obstacle type can be determined. Then, according to the longitudinal distance between the first obstacle and the host vehicle, the first correction coefficient of this first obstacle can be determined, and the initial cut-in duration determined according to the obstacle type of this first obstacle is multiplied by the first correction coefficient of this first obstacle to obtain the cut-in duration for this first obstacle to cut into the lane where the host vehicle is located from its current position.

[0102] It should be understood that Figure 4 the specific values of K and dx in

[0103] In the present application, another implementation of step S1223 includes: determining the product of the first correction coefficient and the initial cut-in duration as the corrected cut-in duration; determining a second correction coefficient corresponding to the target driving style according to the target driving style of the host vehicle selected by the user, and performing a secondary correction on the corrected cut-in duration based on the second correction coefficient to obtain the cut-in duration for the first obstacle to cut into the lane where the host vehicle is located from its current position.

[0104] In this embodiment, in the previous implementation, when considering that the first obstacle has the intention of cutting into the lane where the host vehicle is located, the cut-in method of the first obstacle cutting into the lane where the host vehicle is located is judged according to the distance of the longitudinal distance between the first obstacle and the host vehicle. When the longitudinal distance is relatively close, the cut-in method will be more aggressive, and the first obstacle will cut into the lane where the host vehicle is located at a faster speed; when the longitudinal distance is relatively far, the cut-in method will be more conservative, and the first obstacle will cut into the lane where the host vehicle is located at a slower speed. Therefore, the initial cut-in duration is corrected based on the longitudinal distance between the first obstacle and the host vehicle, so as to ensure that the configured cut-in duration for the first obstacle is more accurate.

[0105] In an actual scenario, different driving styles of the host vehicle will also affect the cut-in duration of the first obstacle. When the driving style of the host vehicle is relatively aggressive, the host vehicle will select the first obstacle as the target obstacle that the host vehicle needs to pay attention to later. At this time, the configured cut-in time for the first obstacle will be smaller to ensure that the host vehicle can select the first obstacle as the target obstacle that the host vehicle needs to pay attention to later; when the driving style of the host vehicle is relatively conservative, the host vehicle will select the first obstacle as the target obstacle that the host vehicle needs to pay attention to earlier. At this time, the configured cut-in time for the first obstacle will be larger to ensure that the host vehicle can select the first obstacle as the target obstacle that the host vehicle needs to pay attention to earlier.

[0106] Therefore, in this embodiment, in another implementation of step S1223, the driver can automatically select the driving style of the host vehicle, such as aggressive, normal, conservative, etc. A corresponding second correction coefficient is configured for each driving style.

[0107] Determine the product of the first correction coefficient of the first obstacle and the initial cut-in duration of the first obstacle as the corrected cut-in duration. Then, according to the driving style of the driver selected on the host vehicle, that is, the target driving style, determine the second correction coefficient corresponding to the target driving style. Determine the product of the corrected cut-in duration and the second correction coefficient as the cut-in duration for the first obstacle to cut into the lane where the host vehicle is located from its current position.

[0108] Exemplarily, different driving styles are set in advance for the host vehicle, and the driving styles are divided into aggressive, normal, and conservative. The second correction coefficient configured for the aggressive driving style is 0.8; the second correction coefficient configured for the normal driving style is 1; the second correction coefficient configured for the conservative driving style is 1.2. According to the target driving style of the host vehicle selected by the driver, the second correction coefficient corresponding to the target driving style is determined. Multiply the corrected cut-in duration of the first obstacle by the second correction coefficient to obtain the cut-in duration for the first obstacle to cut into the lane where the host vehicle is located from its current position.

[0109] In the present application, step S14 specifically includes:

[0110] Step S141: According to the cut-in duration and the lateral driving speed in the obstacle data of the first obstacle, and according to the lateral distance between the first obstacle and the host vehicle, determine the initial predicted position after traveling the cut-in duration during the process of the first obstacle cutting into the lane where the host vehicle is located:

[0111] Step S142: Correct the initial predicted position according to the obstacle size and the obstacle heading angle in the obstacle data of the first obstacle to obtain the predicted position after traveling the cut-in duration during the process of the first obstacle cutting into the lane where the host vehicle is located.

[0112] In this embodiment, the lateral distance between the first obstacle and the host vehicle is determined through the position of the first obstacle relative to the host vehicle in the obstacle data of the first obstacle. Then, according to the cut-in duration of the first obstacle and the lateral driving speed in the obstacle data of the first obstacle, and according to the lateral distance between the first obstacle and the host vehicle, the initial predicted position after traveling the cut-in duration during the process of the first obstacle cutting into the lane where the host vehicle is located is calculated. The formula for calculating the initial predicted position after traveling the cut-in duration during the process of the first obstacle cutting into the lane where the host vehicle is located is as follows:

[0113] D Y = d y + T × V y

[0114] Wherein, D Y is the lateral distance traveled by the first obstacle after traveling the cut-in duration from its current position to cut into the lane where the host vehicle is located; d y is the lateral distance between the host vehicle and the first obstacle at the current moment; T is the cut-in duration; v y is the lateral driving speed of the first obstacle. d y , v y are vectors. When the first obstacle is in the adjacent lane on the left side of the lane where the host vehicle is located, d yis positive, v y is negative; when the first obstacle is located in the adjacent lane on the right side of the lane where the host vehicle is located, d y is negative, v y is positive;

[0115] Since the initial predicted position does not consider the width and attitude information of the first obstacle, in order to obtain a more accurate predicted position, it is necessary to correct the initial predicted position of the first obstacle.

[0116] According to the obstacle size and obstacle heading angle in the obstacle data of the first obstacle, correct the initial predicted position of the first obstacle to obtain the predicted position after driving for the cut-in duration during the process of the first obstacle cutting into the lane where the host vehicle is located. The specific correction formula is as follows:

[0117] The attitude correction amount of the first obstacle is:

[0118] A_d y = sin(a) × Obj_length

[0119] where a is the heading angle of the first obstacle; Obj_length is the length of the first obstacle; the attitude correction amount is a vector, and it is positive when the first obstacle travels to the left in the vehicle body coordinate system and negative when it travels to the right.

[0120] When the first obstacle is on the left side of the host vehicle, the predicted position is:

[0121] |f_D Y | = |d y + D Y + A_d y - Obj_width / 2|

[0122] When the first obstacle is on the right side of the host vehicle, the predicted position is:

[0123] |f_D Y | = |d y + D Y + A_d y + Obj_width / 2|

[0124] where Obj_width is the width of the first obstacle.

[0125] In this application, step S15 specifically includes:

[0126] Step S151: Determine the target probability strategy corresponding to the obstacle type according to the obstacle type of the first obstacle. The target probability strategy characterizes the corresponding relationship between the distance between the center line of the first obstacle under this obstacle type and the center line of the lane where the host vehicle is located and the cut-in probability;

[0127] Step S152: Determine the distance between the center line of the first obstacle and the center line of the lane where the host vehicle is located according to the predicted position.

[0128] Step S153: Determine the cut-in probability of the first obstacle cutting into the lane where the host vehicle is located according to the distance and the target probability strategy.

[0129] In this embodiment, since the driving states of obstacles of different obstacle types are different. For example, a household car has a faster driving speed and a shorter braking time; while a truck has a slower driving speed and a longer braking time; for obstacle types such as motorcycles, bicycles, and pedestrians, although their driving speeds are relatively slow, their movements are more flexible. Therefore, for the first obstacle of different obstacle types at the same predicted position, the corresponding cut-in probabilities are different.

[0130] For example, if the predicted position of a household car obtained by prediction just exceeds the lane line of the lane where the host vehicle is located, at this time, due to the large volume of the household car, it often happens that it just presses on the adjacent lane line during driving. Therefore, for the first obstacle of the household car obstacle type that just exceeds the lane line of the lane where the host vehicle is located, its corresponding cut-in probability will be relatively low, that is, the probability of this first obstacle cutting into the lane where the host vehicle is located is relatively low. For a first obstacle of an obstacle type such as a bicycle or a pedestrian, since it is more flexible during the driving process, when such a first obstacle exceeds the lane line of the lane where the host vehicle is located, its corresponding cut-in probability will be relatively high, that is, the probability of this first obstacle cutting into the lane where the host vehicle is located is relatively high.

[0131] Therefore, in order to make the determined cut-in probability of the first obstacle more accurate, a corresponding probability determination method is configured for each obstacle type to ensure that the probability determination of the first obstacle of different obstacle types is more accurate.

[0132] Therefore, a corresponding target probability strategy is configured for each obstacle type, and the obstacle type and the target probability strategy are in one-to-one correspondence. The target probability strategy corresponding to the obstacle type represents the corresponding relationship between the distance between the center line of the first obstacle of this obstacle type and the center line of the lane where the host vehicle is located and the cut-in probability, that is, the corresponding relationship between this distance and the cut-in probability.

[0133] According to the obstacle type of the first obstacle, the target probability strategy corresponding to this obstacle type can be determined.

[0134] According to the predicted position of the first obstacle, the distance between the center line of the first obstacle and the center line of the lane where the host vehicle is located can be determined. By querying in this target probability strategy, the cut-in probability corresponding to this distance in this target probability strategy can be determined, and this cut-in probability is the cut-in probability of the first obstacle.

[0135] Exemplarily, Figure 5 is a schematic diagram of a target probability strategy in a method for determining a cut-in target concerned by a host vehicle shown in an embodiment of the present application. Refer to Figure 5 , taking the example that the first obstacle cuts into the lane where the host vehicle is located from left to right for illustration. m on the x-axis represents the distance between the center line of the first obstacle and the left lane line of the lane where the host vehicle is located; Pro on the y-axis represents the cut-in probability. According to the obstacle type of the first obstacle, the target probability strategy corresponding to this obstacle type can be determined. Then, the cut-in probability Pro value of the first obstacle can be determined according to the value of the lateral distance m between the first obstacle and the host vehicle.

[0136] In the present application, step S16 specifically includes:

[0137] Step S161: Determine a target probability threshold corresponding to the obstacle type of the first obstacle according to the obstacle type of the first obstacle;

[0138] Step S162: When the cut-in probability exceeds the target probability threshold, determine that the first obstacle is a target obstacle that the host vehicle needs to pay attention to.

[0139] In this embodiment, after calculating the cut-in probability of the first obstacle, since different obstacles have different intensities that the host vehicle needs to pay attention to. For example, a truck is huge in size. When it has the intention of cutting into the lane where the host vehicle is located, the host vehicle is relatively small in volume compared to the truck, and it will be very dangerous if it collides with the host vehicle. Therefore, the attention intensity for the truck will be higher. Even if the calculated cut-in probability of the first obstacle such as a truck is small, it will still be regarded as a target obstacle that the host vehicle needs to pay attention to. Therefore, in order to more accurately determine the target obstacles that the host vehicle needs to pay attention to from the first obstacles, a corresponding target probability threshold is configured for each obstacle type. According to the obstacle type of the first obstacle, determine the target probability threshold corresponding to this obstacle type. When the cut-in probability of this first obstacle exceeds the determined target probability threshold, determine this first obstacle as a target obstacle that the host vehicle needs to pay attention to.

[0140] In this embodiment, it is preferable to configure a target probability threshold of 0.4 for a household car; configure a target probability threshold of 0.3 for a truck; configure a target probability threshold of 0.6 for a pedestrian, a bicycle, and a motorcycle. It should be understood that the different target probability thresholds configured for different obstacle types are only a preferred implementation manner and do not limit the target probability threshold in the present application.

[0141] A method for determining a target of interest of a host vehicle according to the present invention can more accurately determine obstacles in the two adjacent lanes of the lane where the host vehicle is located from the obstacles on the current road by fusing various data information. And subsequently, when determining whether an obstacle is an obstacle that the host vehicle needs to pay attention to, only the obstacles in the two adjacent lanes of the lane where the host vehicle is located are determined, and other obstacles on the current road are no longer concerned. Therefore, the determination efficiency can be effectively improved. And based on the relevant driving data of the obstacle, the predicted position where the obstacle is located after driving for the cut-in duration calculated for the obstacle is predicted. According to the positional relationship between the predicted position and the lane where the host vehicle is located, it is predicted in advance whether the obstacle is a target obstacle that the host vehicle needs to pay attention to. Thus, it can be predicted in advance whether the obstacle is a target obstacle that the host vehicle needs to pay attention to, and in this way, the obstacles that the host vehicle needs to pay attention to can be determined more ahead of time to ensure the safe driving of the host vehicle.

[0142] An embodiment of the present invention further provides a device 600 for determining a cut-in target of interest of a host vehicle. Figure 6 It is a schematic diagram of a device for determining a cut-in target of interest of a host vehicle shown in an embodiment of the present application. Refer to Figure 6 , the present application provides a device 600 for determining a cut-in target of interest of a host vehicle, including:

[0143] A data acquisition module 601, configured to acquire map data, road data, and obstacle data;

[0144] A first obstacle determination module 602, configured to fuse the map data, the road data, and the obstacle data to determine a first obstacle in the adjacent lanes of the lane where the host vehicle is located from the obstacles on the current road;

[0145] A cut-in duration determination module 603, configured to determine the cut-in duration for the first obstacle to cut into the lane where the host vehicle is located from its current position according to the obstacle type in the obstacle data and the position of the obstacle relative to the host vehicle;

[0146] A position prediction module 604, configured to determine the predicted position where the first obstacle is located after driving for the cut-in duration during the process of cutting into the lane where the host vehicle is located according to the cut-in duration, the lateral driving speed of the obstacle in the obstacle data, and the position of the obstacle relative to the host vehicle;

[0147] The cut-in probability calculation module 605 is configured to determine the cut-in probability of the first obstacle cutting into the lane where the host vehicle is located according to the positional relationship between the predicted position and the lane where the host vehicle is located.

[0148] The target obstacle determination module 606 is configured to determine whether the first obstacle is a target obstacle that the host vehicle needs to pay attention to according to the cut-in probability and a preset probability threshold.

[0149] In the present application, the first obstacle determination module 602 includes:

[0150] The road fusion module is configured to perform road fusion on the map data and the road data to obtain lane parameter information of the current road.

[0151] The perception fusion module is configured to perform perception fusion on the lane parameter information and the obstacle data to determine a first obstacle in the adjacent lane of the lane where the host vehicle is located from the obstacles on the current road.

[0152] In the present application, the cut-in duration determination module 603 includes:

[0153] The initial cut-in duration determination module is configured to determine an initial cut-in duration corresponding to the obstacle type of the first obstacle according to the obstacle type in the obstacle data of the first obstacle.

[0154] The cut-in duration determination module is configured to correct the initial cut-in duration according to the longitudinal distance between the first obstacle and the host vehicle and the obstacle type of the first obstacle to obtain the cut-in duration of the first obstacle cutting into the lane where the host vehicle is located from its current position.

[0155] In the present application, the cut-in duration determination module includes:

[0156] The correction strategy determination module is configured to determine a target correction strategy corresponding to the obstacle type according to the obstacle type of the first obstacle, and the target correction strategy represents the corresponding relationship between the longitudinal distance between the first obstacle of this obstacle type and the host vehicle and a first correction coefficient.

[0157] The first correction coefficient determination module is configured to determine a first correction coefficient according to the longitudinal distance between the first obstacle and the host vehicle and the target correction strategy.

[0158] The cut-in duration determination sub-module is configured to determine the product of the first correction coefficient and the initial cut-in duration as the cut-in duration of the first obstacle cutting into the lane where the host vehicle is located from its current position.

[0159] In the present application, the cut-in duration determination sub-module includes:

[0160] A corrected cut-in duration calculation module, configured to determine the corrected cut-in duration as the product of the first correction coefficient and the initial cut-in duration;

[0161] A cut-in duration calculation module, configured to determine a second correction coefficient corresponding to the target driving style according to the target driving style of the host vehicle selected by the user, and perform a secondary correction on the corrected cut-in duration based on the second correction coefficient to obtain the cut-in duration for the first obstacle to cut into the lane where the host vehicle is located from its current position.

[0162] In the present application, the position prediction module 604 includes:

[0163] An initial position prediction module, configured to determine an initial predicted position after traveling the cut-in duration during the process of the first obstacle cutting into the lane where the host vehicle is located according to the cut-in duration and the lateral traveling speed in the obstacle data of the first obstacle, and according to the lateral distance between the first obstacle and the host vehicle;

[0164] A position prediction sub-module, configured to correct the initial predicted position according to the obstacle size and the obstacle heading angle in the obstacle data of the first obstacle to obtain the predicted position after traveling the cut-in duration during the process of the first obstacle cutting into the lane where the host vehicle is located.

[0165] In the present application, the cut-in probability calculation module 605 includes:

[0166] A target probability strategy determination module, configured to determine a target probability strategy corresponding to the obstacle type according to the obstacle type of the first obstacle, where the target probability strategy represents the corresponding relationship between the distance between the center line of the first obstacle of this obstacle type and the center line of the lane where the host vehicle is located and the cut-in probability;

[0167] A distance determination module, configured to determine the distance between the center line of the first obstacle and the center line of the lane where the host vehicle is located according to the predicted position;

[0168] A cut-in probability calculation sub-module, configured to determine the cut-in probability of the first obstacle cutting into the lane where the host vehicle is located according to the distance and the target probability strategy.

[0169] In the present application, the target obstacle determination module 606 includes:

[0170] A target probability threshold determination module, configured to determine a target probability threshold corresponding to the obstacle type of the first obstacle according to the obstacle type of the first obstacle;

[0171] A target obstacle determination sub-module, configured to determine that the first obstacle is a target obstacle that the host vehicle needs to pay attention to when the cut-in probability exceeds the target probability threshold.

[0172] An embodiment of the present invention further provides a vehicle, which may specifically include: the above device for determining a cut-in target that the host vehicle pays attention to, and is configured to execute the steps in the method for determining a cut-in target that the host vehicle pays attention to.

[0173] An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps in the above method for determining a cut-in target that the host vehicle pays attention to are implemented.

[0174] The foregoing is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for determining a cut-in target of interest to a vehicle, characterized in that: The method comprises: Obtain map data, road data, and obstacle data through on-board sensors; The map data, the road data and the obstacle data are integrated to determine a first obstacle located in a lane adjacent to a lane where the vehicle is located from obstacles on the current road; Determine, according to the obstacle type in the obstacle data and the position of the obstacle relative to the ego vehicle, the cutting-in time of the first obstacle from its current position into the lane where the ego vehicle is located; Determine, according to the cut-in duration, the lateral speed of the obstacle in the obstacle data, and the position of the obstacle relative to the vehicle, a predicted position of the first obstacle after traveling the cut-in duration in the process of cutting into the lane where the vehicle is located; Determining a probability of the first obstacle cutting into the lane where the ego vehicle is located according to a positional relationship between the predicted position and the lane where the ego vehicle is located; According to the cut-in probability and a preset probability threshold, it is determined whether the first obstacle is a target obstacle that the ego vehicle needs to pay attention to.

2. The method according to claim 1, characterized in that The step of fusing the map data, the road data and the obstacle data to determine, from obstacles on the current road, a first obstacle in a lane adjacent to a lane where the vehicle is located, includes: Fusing the map data with the road data to obtain lane parameter information of the current road; The lane parameter information and the obstacle data are sensed and fused to determine a first obstacle in a lane adjacent to a lane where the vehicle is located from obstacles on the current road.

3. The method according to claim 1, characterized in that The determining, according to the obstacle type in the obstacle data and the position of the obstacle relative to the vehicle, the cutting-in time of the first obstacle from its current position into the lane where the vehicle is located, comprises: Determining, according to the obstacle type in the obstacle data of the first obstacle, an initial cut-in duration corresponding to the obstacle type of the first obstacle; The initial cut-in duration is corrected according to the longitudinal distance between the first obstacle and the ego vehicle and the obstacle type of the first obstacle to obtain the cut-in duration of the first obstacle cutting into the lane where the ego vehicle is located from its current position.

4. The method according to claim 3, characterized in that The step of correcting the initial cut-in duration according to the longitudinal distance between the first obstacle and the vehicle and the obstacle type of the first obstacle to obtain the cut-in duration of the first obstacle from its current position into the lane where the vehicle is located includes: Determining, according to the obstacle type of the first obstacle, a target correction strategy corresponding to the obstacle type, wherein the target correction strategy represents a corresponding relationship between a longitudinal distance between the first obstacle and the vehicle under the obstacle type and a first correction coefficient; determining a first correction coefficient according to the longitudinal distance between the first obstacle and the ego vehicle and the target correction strategy; The product of the first correction coefficient and the initial cut-in time is determined as the cut-in time of the first obstacle from its current position into the lane where the vehicle is located.

5. The method according to claim 4, characterized in that The step of multiplying the first correction coefficient by the initial cut-in time to determine the cut-in time of the first obstacle from its current position into the lane where the vehicle is located includes: Determine the product of the first correction coefficient and the initial cut-in duration as the corrected cut-in duration; According to the target driving style of the vehicle selected by the user, a second correction coefficient corresponding to the target driving style is determined, and the corrected cut-in duration is secondarily corrected based on the second correction coefficient to obtain the cut-in duration of the first obstacle cutting into the lane where the vehicle is located from its current position.

6. The method according to claim 1, characterized in that The determining, according to the cut-in duration, the lateral speed of the obstacle in the obstacle data, and the position of the obstacle relative to the vehicle, a predicted position of the first obstacle after traveling the cut-in duration in the process of cutting into the lane where the vehicle is located, includes: Determine, according to the cut-in duration and the lateral speed of the obstacle in the obstacle data of the first obstacle, and according to the lateral distance of the first obstacle relative to the ego vehicle, an initial predicted position of the first obstacle after traveling the cut-in duration in the process of cutting into the lane where the ego vehicle is located; The initial predicted position is corrected according to the obstacle size and obstacle heading angle in the obstacle data of the first obstacle to obtain a predicted position of the first obstacle after the vehicle cuts in for the cut-in time.

7. The method according to claim 1, characterized in that The determining, based on the positional relationship between the predicted position and the lane where the vehicle is located, a probability of the first obstacle cutting into the lane where the vehicle is located, includes: Determining, according to the obstacle type of the first obstacle, a target probability strategy corresponding to the obstacle type, wherein the target probability strategy represents a corresponding relationship between a distance between a center line of the first obstacle and a center line of a lane where the vehicle is located and a cut-in probability under the obstacle type; Determining, based on the predicted position, a distance between a center line of the first obstacle and a center line of a lane where the vehicle is located; The cutting-in probability of the first obstacle cutting-into the lane where the ego vehicle is located is determined according to the distance and the target probability strategy.

8. The method according to claim 1, characterized in that The determining, based on the cut-in probability and a preset probability threshold, whether the first obstacle is a target obstacle that the ego vehicle needs to pay attention to includes: determining, according to the obstacle type of the first obstacle, a target probability threshold corresponding to the obstacle type of the first obstacle; When the cut-in probability exceeds the target probability threshold, the first obstacle is determined to be a target obstacle that the ego vehicle needs to pay attention to.

9. A device for determining a cut-in target of interest to a vehicle, characterized in that: The device comprises: A data acquisition module, used to acquire map data, road data and obstacle data; a first obstacle determination module, configured to fuse the map data, the road data and the obstacle data, so as to determine, from obstacles on the current road, a first obstacle in a lane adjacent to the lane where the vehicle is located; a cut-in time determination module, configured to determine a cut-in time for the first obstacle to cut into the lane where the vehicle is located from its current position according to the obstacle type in the obstacle data and the position of the obstacle relative to the vehicle; a position prediction module, for determining a predicted position of the first obstacle after the first obstacle has traveled the cut-in time in the process of cutting into the lane where the vehicle is located, according to the cut-in time, the lateral speed of the obstacle in the obstacle data, and the position of the obstacle relative to the vehicle; a cut-in probability calculation module, used to determine a cut-in probability of the first obstacle cutting into the lane where the ego vehicle is located according to a positional relationship between the predicted position and the lane where the ego vehicle is located; The target obstacle determination module is used to determine whether the first obstacle is a target obstacle that the ego vehicle needs to pay attention to based on the cut-in probability and a preset probability threshold.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the method for determining a cut-in target of interest to the vehicle are implemented as described in any one of claims 1 to 8.

Images